Wasserstein Barycenter is a principled approach to represent the weighted mean of a given set of probability distributions, utilizing the geometry induced by optimal transport. In this work, we present a novel scalable algorithm to approximate the Wasserstein Barycenters aiming at high-dimensional applications in machine learning. Our proposed algorithm is based on the Kantorovich dual formulation of the Wasserstein-2 distance as well as a recent neural network architecture, input convex neural network, that is known to parametrize convex functions. The distinguishing features of our method are: i) it only requires samples from the marginal distributions; ii) unlike the existing approaches, it represents the Barycenter with a generative model and can thus generate infinite samples from the barycenter without querying the marginal distributions; iii) it works similar to Generative Adversarial Model in one marginal case. We demonstratethe efficacy of our algorithm by comparing it with the state-of-art methods in multiple experiments.

Bayesian optimization (BO) is among the most effective and widely-used blackbox optimization methods. BO proposes solutions according to an explore-exploit trade-off criterion encoded in an acquisition function, many of which are computed from the posterior predictive of a probabilistic surrogate model. Prevalent among these is the expected improvement (EI). The need to ensure analytical tractability of the predictive often poses limitations that can hinder the efficiency and applicability of BO. In this paper, we cast the computation of EI as a binary classification problem, building on the link between class-probability estimation and density-ratio estimation, and the lesser-known link between density-ratios and EI. By circumventing the tractability constraints, this reformulation provides numerous advantages, not least in terms of expressiveness, versatility, and scalability.

Attention-based architectures have become ubiquitous in machine learning. Yet, our understanding of the reasons for their effectiveness remains limited. This work proposes a new way to understand self-attention networks: we show that their output can be decomposed into a sum of smaller terms---or paths---each involving the operation of a sequence of attention heads across layers. Using this path decomposition, we prove that self-attention possesses a strong inductive bias towards "token uniformity". Specifically, without skip connections or multi-layer perceptrons (MLPs), the output converges doubly exponentially to a rank-1 matrix. On the other hand, skip connections and MLPs stop the output from degeneration. Our experiments verify the convergence results on standard transformer architectures.

Existing evaluation suites for multi-agent reinforcement learning (MARL) do not assess generalization to novel situations as their primary objective (unlike supervised learning benchmarks). Our contribution, Melting Pot, is a MARL evaluation suite that fills this gap and uses reinforcement learning to reduce the human labor required to create novel test scenarios. This works because one agent's behavior constitutes (part of) another agent's environment. To demonstrate scalability, we have created over 80 unique test scenarios covering a broad range of research topics such as social dilemmas, reciprocity, resource sharing, and task partitioning. We apply these test scenarios to standard MARL training algorithms, and demonstrate how Melting Pot reveals weaknesses not apparent from training performance alone.

Recent advances in Transformer models allow for unprecedented sequence lengths, due to linear space and time complexity. In the meantime, relative positional encoding (RPE) was proposed as beneficial for classical Transformers and consists in exploiting lags instead of absolute positions for inference. Still, RPE is not available for the recent linear-variants of the Transformer, because it requires the explicit computation of the attention matrix, which is precisely what is avoided by such methods. In this paper, we bridge this gap and present Stochastic Positional Encoding as a way to generate PE that can be used as a replacement to the classical additive (sinusoidal) PE and provably behaves like RPE. The main theoretical contribution is to make a connection between positional encoding and cross-covariance structures of correlated Gaussian processes. We illustrate the performance of our approach on the Long-Range Arena benchmark and on music generation.

Decentralization is a promising method of scaling up parallel machine learning systems. In this paper, we provide a tight lower bound on the iteration complexity for such methods in a stochastic non-convex setting. Our lower bound reveals a theoretical gap in known convergence rates of many existing decentralized training algorithms, such as D-PSGD. We prove by construction this lower bound is tight and achievable. Motivated by our insights, we further propose DeTAG, a practical gossip-style decentralized algorithm that achieves the lower bound with only a logarithm gap. Empirically, we compare DeTAG with other decentralized algorithms on image classification tasks, and we show DeTAG enjoys faster convergence compared to baselines, especially on unshuffled data and in sparse networks.

Off-policy evaluation learns a target policy's value with a historical dataset generated by a different behavior policy. In addition to a point estimate, many applications would benefit significantly from having a confidence interval (CI) that quantifies the uncertainty of the point estimate. In this paper, we propose a novel procedure to construct an efficient, robust, and flexible CI on a target policy's value. Our method is justified by theoretical results and numerical experiments. A Python implementation of the proposed procedure is available at https://github.com/ RunzheStat/D2OPE.

We introduce Phasic Policy Gradient (PPG), a reinforcement learning framework which modifies traditional on-policy actor-critic methods by separating policy and value function training into distinct phases. In prior methods, one must choose between using a shared network or separate networks to represent the policy and value function. Using separate networks avoids interference between objectives, while using a shared network allows useful features to be shared. PPG is able to achieve the best of both worlds by splitting optimization into two phases, one that advances training and one that distills features. PPG also enables the value function to be more aggressively optimized with a higher level of sample reuse. Compared to PPO, we find that PPG significantly improves sample efficiency on the challenging Procgen Benchmark.

In general, graph representation learning methods assume that the train and test data come from the same distribution. In this work we consider an underexplored area of an otherwise rapidly developing field of graph representation learning: The task of out-of-distribution (OOD) graph classification, where train and test data have different distributions, with test data unavailable during training. Our work shows it is possible to use a causal model to learn approximately invariant representations that better extrapolate between train and test data. Finally, we conclude with synthetic and real-world dataset experiments showcasing the benefits of representations that are invariant to train/test distribution shifts.

We propose a general and scalable approximate sampling strategy for probabilistic models with discrete variables. Our approach uses gradients of the likelihood function with respect to its discrete inputs to propose updates in a Metropolis-Hastings sampler. We show empirically that this approach outperforms generic samplers in a number of difficult settings including Ising models, Potts models, restricted Boltzmann machines, and factorial hidden Markov models. We also demonstrate our improved sampler for training deep energy-based models on high dimensional discrete image data. This approach outperforms variational auto-encoders and existing energy-based models. Finally, we give bounds showing that our approach is near-optimal in the class of samplers which propose local updates.

In this paper we cast neural networks defined on graphs as message-passing neural networks (MPNNs) to study the distinguishing power of different classes of such models. We are interested in when certain architectures are able to tell vertices apart based on the feature labels given as input with the graph. We consider two variants of MPNNS: anonymous MPNNs whose message functions depend only on the labels of vertices involved; and degree-aware MPNNs whose message functions can additionally use information regarding the degree of vertices. The former class covers popular graph neural network (GNN) formalisms for which the distinguished power is known. The latter covers graph convolutional networks (GCNs), introduced by Kipf and Welling, for which the distinguishing power was unknown. We obtain lower and upper bounds on the distinguishing power of (anonymous and degree-aware) MPNNs in terms of the distinguishing power of the Weisfeiler-Lehman (WL) algorithm. Our main results imply that (i) the distinguishing power of GCNs is bounded by the WL algorithm, but they may be one step ahead; (ii) the WL algorithm cannot be simulated by ``plain vanilla'' GCNs but the addition of a trade-off parameter between features of the vertex and those of its neighbours (as proposed …

We study function approximation for episodic reinforcement learning with entropic risk measure. We first propose an algorithm with linear function approximation. Compared to existing algorithms, which suffer from improper regularization and regression biases, this algorithm features debiasing transformations in backward induction and regression procedures. We further propose an algorithm with general function approximation, which features implicit debiasing transformations. We prove that both algorithms achieve a sublinear regret and demonstrate a trade-off between generality and efficiency. Our analysis provides a unified framework for function approximation in risk-sensitive reinforcement learning, which leads to the first sublinear regret bounds in the setting.

We consider the construction of neural network architectures for data on simplicial complexes. In studying maps on the chain complex of a simplicial complex, we define three desirable properties of a simplicial neural network architecture: namely, permutation equivariance, orientation equivariance, and simplicial awareness. The first two properties respectively account for the fact that the node indexing and the simplex orientations in a simplicial complex are arbitrary. The last property encodes the desirable feature that the output of the neural network depends on the entire simplicial complex and not on a subset of its dimensions. Based on these properties, we propose a simple convolutional architecture, rooted in tools from algebraic topology, for the problem of trajectory prediction, and show that it obeys all three of these properties when an odd, nonlinear activation function is used. We then demonstrate the effectiveness of this architecture in extrapolating trajectories on synthetic and real datasets, with particular emphasis on the gains in generalizability to unseen trajectories.

We show how fitting sparse linear models over learned deep feature representations can lead to more debuggable neural networks. These networks remain highly accurate while also being more amenable to human interpretation, as we demonstrate quantitatively and via human experiments. We further illustrate how the resulting sparse explanations can help to identify spurious correlations, explain misclassifications, and diagnose model biases in vision and language tasks.

The time and effort involved in hand-designing deep neural networks is immense. This has prompted the development of Neural Architecture Search (NAS) techniques to automate this design. However, NAS algorithms tend to be slow and expensive; they need to train vast numbers of candidate networks to inform the search process. This could be alleviated if we could partially predict a network's trained accuracy from its initial state. In this work, we examine the overlap of activations between datapoints in untrained networks and motivate how this can give a measure which is usefully indicative of a network’s trained performance. We incorporate this measure into a simple algorithm that allows us to search for powerful networks without any training in a matter of seconds on a single GPU, and verify its effectiveness on NAS-Bench-101, NAS-Bench-201, NATS-Bench, and Network Design Spaces. Our approach can be readily combined with more expensive search methods; we examine a simple adaptation of regularised evolutionary search. Code for reproducing our experiments is available at https://github.com/BayesWatch/nas-without-training.

The posterior over Bayesian neural network (BNN) parameters is extremely high-dimensional and non-convex. For computational reasons, researchers approximate this posterior using inexpensive mini-batch methods such as mean-field variational inference or stochastic-gradient Markov chain Monte Carlo (SGMCMC). To investigate foundational questions in Bayesian deep learning, we instead use full batch Hamiltonian Monte Carlo (HMC) on modern architectures. We show that (1) BNNs can achieve significant performance gains over standard training and deep ensembles; (2) a single long HMC chain can provide a comparable representation of the posterior to multiple shorter chains; (3) in contrast to recent studies, we find posterior tempering is not needed for near-optimal performance, with little evidence for a ``cold posterior'' effect, which we show is largely an artifact of data augmentation; (4) BMA performance is robust to the choice of prior scale, and relatively similar for diagonal Gaussian, mixture of Gaussian, and logistic priors; (5) Bayesian neural networks show surprisingly poor generalization under domain shift; (6) while cheaper alternatives such as deep ensembles and SGMCMC can provide good generalization, their predictive distributions are distinct from HMC. Notably, deep ensemble predictive distributions are similarly close to HMC as standard SGLD, and closer than standard variational inference.

Stochastic gradient algorithms are often unstable when applied to functions that do not have Lipschitz-continuous and/or bounded gradients. Gradient clipping is a simple and effective technique to stabilize the training process for problems that are prone to the exploding gradient problem. Despite its widespread popularity, the convergence properties of the gradient clipping heuristic are poorly understood, especially for stochastic problems. This paper establishes both qualitative and quantitative convergence results of the clipped stochastic (sub)gradient method (SGD) for non-smooth convex functions with rapidly growing subgradients. Our analyses show that clipping enhances the stability of SGD and that the clipped SGD algorithm enjoys finite convergence rates in many cases. We also study the convergence of a clipped method with momentum, which includes clipped SGD as a special case, for weakly convex problems under standard assumptions. With a novel Lyapunov analysis, we show that the proposed method achieves the best-known rate for the considered class of problems, demonstrating the effectiveness of clipped methods also in this regime. Numerical results confirm our theoretical developments.

This paper proposes Omnidirectional Representations from Transformers (OMNINET). In OmniNet, instead of maintaining a strictly horizon-tal receptive field, each token is allowed to attend to all tokens in the entire network. This process can also be interpreted as a form of extreme or intensive attention mechanism that has the receptive field of the entire width and depth of the network. To this end, the omnidirectional attention is learned via a meta-learner, which is essentially another self-attention based model. In order to mitigate the computationally expensive costs of full receptive field attention, we leverage efficient self-attention models such as kernel-based, low-rank attention and/or Big Bird as the meta-learner. Extensive experiments are conducted on autoregressive language modeling(LM1B, C4), Machine Translation, Long Range Arena (LRA), and Image Recognition.The experiments show that OmniNet achieves considerable improvements across these tasks, including achieving state-of-the-art performance on LM1B,WMT’14 En-De/En-Fr, and Long Range Arena.Moreover, using omnidirectional representation in Vision Transformers leads to significant improvements on image recognition tasks on both few-shot learning and fine-tuning setups.

In real-world multi-agent systems, agents with different capabilities may join or leave without altering the team's overarching goals. Coordinating teams with such dynamic composition is challenging: the optimal team strategy varies with the composition. We propose COPA, a coach-player framework to tackle this problem. We assume the coach has a global view of the environment and coordinates the players, who only have partial views, by distributing individual strategies. Specifically, we 1) adopt the attention mechanism for both the coach and the players; 2) propose a variational objective to regularize learning; and 3) design an adaptive communication method to let the coach decide when to communicate with the players. We validate our methods on a resource collection task, a rescue game, and the StarCraft micromanagement tasks. We demonstrate zero-shot generalization to new team compositions. Our method achieves comparable or better performance than the setting where all players have a full view of the environment. Moreover, we see that the performance remains high even when the coach communicates as little as 13% of the time using the adaptive communication strategy.

Planning, the ability to analyze the structure of a problem in the large and decompose it into interrelated subproblems, is a hallmark of human intelligence. While deep reinforcement learning (RL) has shown great promise for solving relatively straightforward control tasks, it remains an open problem how to best incorporate planning into existing deep RL paradigms to handle increasingly complex environments. One prominent framework, Model-Based RL, learns a world model and plans using step-by-step virtual rollouts. This type of world model quickly diverges from reality when the planning horizon increases, thus struggling at long-horizon planning. How can we learn world models that endow agents with the ability to do temporally extended reasoning? In this work, we propose to learn graph-structured world models composed of sparse, multi-step transitions. We devise a novel algorithm to learn latent landmarks that are scattered (in terms of reachability) across the goal space as the nodes on the graph. In this same graph, the edges are the reachability estimates distilled from Q-functions. On a variety of high-dimensional continuous control tasks ranging from robotic manipulation to navigation, we demonstrate that our method, named L3P, significantly outperforms prior work, and is oftentimes the only method capable of leveraging both …

Vision-and-Language Pre-training (VLP) has improved performance on various joint vision-and-language downstream tasks. Current approaches to VLP heavily rely on image feature extraction processes, most of which involve region supervision (e.g., object detection) and the convolutional architecture (e.g., ResNet). Although disregarded in the literature, we find it problematic in terms of both (1) efficiency/speed, that simply extracting input features requires much more computation than the multimodal interaction steps; and (2) expressive power, as it is upper bounded to the expressive power of the visual embedder and its predefined visual vocabulary. In this paper, we present a minimal VLP model, Vision-and-Language Transformer (ViLT), monolithic in the sense that the processing of visual inputs is drastically simplified to just the same convolution-free manner that we process textual inputs. We show that ViLT is up to tens of times faster than previous VLP models, yet with competitive or better downstream task performance. Our code and pre-trained weights are available at https://github.com/dandelin/vilt.

We introduce a new skill-discovery algorithm that builds a discrete graph representation of large continuous MDPs, where nodes correspond to skill subgoals and the edges to skill policies. The agent constructs this graph during an unsupervised training phase where it interleaves discovering skills and planning using them to gain coverage over ever-increasing portions of the state-space. Given a novel goal at test time, the agent plans with the acquired skill graph to reach a nearby state, then switches to learning to reach the goal. We show that the resulting algorithm, Deep Skill Graphs, outperforms both flat and existing hierarchical reinforcement learning methods on four difficult continuous control tasks.

Attention mechanisms have shown promising results in sequence modeling tasks that require long-term memory. Recent work investigated mechanisms to reduce the computational cost of preserving and storing memories. However, not all content in the past is equally important to remember. We propose Expire-Span, a method that learns to retain the most important information and expire the irrelevant information. This forgetting of memories enables Transformers to scale to attend over tens of thousands of previous timesteps efficiently, as not all states from previous timesteps are preserved. We demonstrate that Expire-Span can help models identify and retain critical information and show it can achieve strong performance on reinforcement learning tasks specifically designed to challenge this functionality. Next, we show that Expire-Span can scale to memories that are tens of thousands in size, setting a new state of the art on incredibly long context tasks such as character-level language modeling and a frame-by-frame moving objects task. Finally, we analyze the efficiency of Expire-Span compared to existing approaches and demonstrate that it trains faster and uses less memory.

Variational autoencoders with deep hierarchies of stochastic layers have been known to suffer from the problem of posterior collapse, where the top layers fall back to the prior and become independent of input. We suggest that the hierarchical VAE objective explicitly includes the variance of the function parameterizing the mean and variance of the latent Gaussian distribution which itself is often a high variance function. Building on this we generalize VAE neural networks by incorporating a smoothing parameter motivated by Gaussian analysis to reduce higher frequency components and consequently the variance in parameterizing functions and show that this can help to solve the problem of posterior collapse. We further show that under such smoothing the VAE loss exhibits a phase transition, where the top layer KL divergence sharply drops to zero at a critical value of the smoothing parameter that is similar for the same model across datasets. We validate the phenomenon across model configurations and datasets.

Softmax classifiers with a very large number of classes naturally occur in many applications such as natural language processing and information retrieval. The calculation of full softmax is costly from the computational and energy perspective. There have been various sampling approaches to overcome this challenge, popularly known as negative sampling (NS). Ideally, NS should sample negative classes from a distribution that is dependent on the input data, the current parameters, and the correct positive class. Unfortunately, due to the dynamically updated parameters and data samples, there is no sampling scheme that is provably adaptive and samples the negative classes efficiently. Therefore, alternative heuristics like random sampling, static frequency-based sampling, or learning-based biased sampling, which primarily trade either the sampling cost or the adaptivity of samples per iteration are adopted. In this paper, we show two classes of distributions where the sampling scheme is truly adaptive and provably generates negative samples in near-constant time. Our implementation in C++ on CPU is significantly superior, both in terms of wall-clock time and accuracy, compared to the most optimized TensorFlow implementations of other popular negative sampling approaches on powerful NVIDIA V100 GPU.

Multi-agent settings in the real world often involve tasks with varying types and quantities of agents and non-agent entities; however, common patterns of behavior often emerge among these agents/entities. Our method aims to leverage these commonalities by asking the question: `What is the expected utility of each agent when only considering a randomly selected sub-group of its observed entities?'' By posing this counterfactual question, we can recognize state-action trajectories within sub-groups of entities that we may have encountered in another task and use what we learned in that task to inform our prediction in the current one. We then reconstruct a prediction of the full returns as a combination of factors considering these disjoint groups of entities and train this`

randomly factorized" value function as an auxiliary objective for value-based multi-agent reinforcement learning. By doing so, our model can recognize and leverage similarities across tasks to improve learning efficiency in a multi-task setting. Our approach, Randomized Entity-wise Factorization for Imagined Learning (REFIL), outperforms all strong baselines by a significant margin in challenging multi-task StarCraft micromanagement settings.

Recent works (White et al., 2020a; Yan et al., 2020) demonstrate the importance of architecture encodings in Neural Architecture Search (NAS). These encodings encode either structure or computation information of the neural architectures. Compared to structure-aware encodings, computation-aware encodings map architectures with similar accuracies to the same region, which improves the downstream architecture search performance (Zhang et al., 2019; White et al., 2020a). In this work, we introduce a Computation-Aware Transformer-based Encoding method called CATE. Different from existing computation-aware encodings based on fixed transformation (e.g. path encoding), CATE employs a pairwise pre-training scheme to learn computation-aware encodings using Transformers with cross-attention. Such learned encodings contain dense and contextualized computation information of neural architectures. We compare CATE with eleven encodings under three major encoding-dependent NAS subroutines in both small and large search spaces. Our experiments show that CATE is beneficial to the downstream search, especially in the large search space. Moreover, the outside search space experiment demonstrates its superior generalization ability beyond the search space on which it was trained. Our code is available at: https://github.com/MSU-MLSys-Lab/CATE.

We propose NeRF-VAE, a 3D scene generative model that incorporates geometric structure via Neural Radiance Fields (NeRF) and differentiable volume rendering. In contrast to NeRF, our model takes into account shared structure across scenes, and is able to infer the structure of a novel scene---without the need to re-train---using amortized inference. NeRF-VAE's explicit 3D rendering process further contrasts previous generative models with convolution-based rendering which lacks geometric structure. Our model is a VAE that learns a distribution over radiance fields by conditioning them on a latent scene representation. We show that, once trained, NeRF-VAE is able to infer and render geometrically-consistent scenes from previously unseen 3D environments of synthetic scenes using very few input images. We further demonstrate that NeRF-VAE generalizes well to out-of-distribution cameras, while convolutional models do not. Finally, we introduce and study an attention-based conditioning mechanism of NeRF-VAE's decoder, which improves model performance.

Humans are accustomed to environments that contain both regularities and exceptions. For example, at most gas stations, one pays prior to pumping, but the occasional rural station does not accept payment in advance. Likewise, deep neural networks can generalize across instances that share common patterns or structures, yet have the capacity to memorize rare or irregular forms. We analyze how individual instances are treated by a model via a consistency score. The score characterizes the expected accuracy for a held-out instance given training sets of varying size sampled from the data distribution. We obtain empirical estimates of this score for individual instances in multiple data sets, and we show that the score identifies out-of-distribution and mislabeled examples at one end of the continuum and strongly regular examples at the other end. We identify computationally inexpensive proxies to the consistency score using statistics collected during training. We apply the score toward understanding the dynamics of representation learning and to filter outliers during training.

Policies for partially observed Markov decision processes can be efficiently learned by imitating expert policies generated using asymmetric information. Unfortunately, existing approaches for this kind of imitation learning have a serious flaw: the expert does not know what the trainee cannot see, and as a result may encourage actions that are sub-optimal or unsafe under partial information. To address this issue, we derive an update which, when applied iteratively to an expert, maximizes the expected reward of the trainee's policy. Using this update, we construct a computationally efficient algorithm, adaptive asymmetric DAgger (A2D), that jointly trains the expert and trainee policies. We then show that A2D allows the trainee to safely imitate the modified expert, and outperforms policies learned either by imitating a fixed expert or through direct reinforcement learning.

Unrolled computation graphs arise in many scenarios, including training RNNs, tuning hyperparameters through unrolled optimization, and training learned optimizers. Current approaches to optimizing parameters in such computation graphs suffer from high variance gradients, bias, slow updates, or large memory usage. We introduce a method called Persistent Evolution Strategies (PES), which divides the computation graph into a series of truncated unrolls, and performs an evolution strategies-based update step after each unroll. PES eliminates bias from these truncations by accumulating correction terms over the entire sequence of unrolls. PES allows for rapid parameter updates, has low memory usage, is unbiased, and has reasonable variance characteristics. We experimentally demonstrate the advantages of PES compared to several other methods for gradient estimation on synthetic tasks, and show its applicability to training learned optimizers and tuning hyperparameters.

In the stochastic submodular cover problem, the goal is to select a subset of stochastic items of minimum expected cost to cover a submodular function. Solutions in this setting correspond to a sequential decision process that selects items one by one ``adaptively'' (depending on prior observations). While such adaptive solutions achieve the best objective, the inherently sequential nature makes them undesirable in many applications. We ask: \emph{how well can solutions with only a few adaptive rounds approximate fully-adaptive solutions?} We consider both cases where the stochastic items are independent, and where they are correlated. For both situations, we obtain nearly tight answers, establishing smooth tradeoffs between the number of adaptive rounds and the solution quality, relative to fully adaptive solutions. Experiments on synthetic and real datasets validate the practical performance of our algorithms, showing qualitative improvements in the solutions as we allow more rounds of adaptivity; in practice, solutions using just a few rounds of adaptivity are nearly as good as fully adaptive solutions.

Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow practitioners to instead interactively teach agents through tailored feedback; however, such approaches have been challenging to scale since human feedback is very expensive. In this work, we aim to make this process more sample- and feedback-efficient. We present an off-policy, interactive RL algorithm that capitalizes on the strengths of both feedback and off-policy learning. Specifically, we learn a reward model by actively querying a teacher's preferences between two clips of behavior and use it to train an agent. To enable off-policy learning, we relabel all the agent's past experience when its reward model changes. We additionally show that pre-training our agents with unsupervised exploration substantially increases the mileage of its queries. We demonstrate that our approach is capable of learning tasks of higher complexity than previously considered by human-in-the-loop methods, including a variety of locomotion and robotic manipulation skills. We also show that our method is able to utilize real-time human feedback to effectively prevent reward exploitation and learn new behaviors that are difficult to specify with standard reward …

Influence maximization is the task of selecting a small number of seed nodes in a social network to maximize the spread of the influence from these seeds, and it has been widely investigated in the past two decades. In the canonical setting, the whole social network as well as its diffusion parameters is given as input. In this paper, we consider the more realistic sampling setting where the network is unknown and we only have a set of passively observed cascades that record the set of activated nodes at each diffusion step. We study the task of influence maximization from these cascade samples (IMS), and present constant approximation algorithms for this task under mild conditions on the seed set distribution. To achieve the optimization goal, we also provide a novel solution to the network inference problem, that is, learning diffusion parameters and the network structure from the cascade data. Comparing with prior solutions, our network inference algorithm requires weaker assumptions and does not rely on maximum-likelihood estimation and convex programming. Our IMS algorithms enhance the learning-and-then-optimization approach by allowing a constant approximation ratio even when the diffusion parameters are hard to learn, and we do not need any assumption related …

Standard deep reinforcement learning algorithms use a shared representation for the policy and value function, especially when training directly from images. However, we argue that more information is needed to accurately estimate the value function than to learn the optimal policy. Consequently, the use of a shared representation for the policy and value function can lead to overfitting. To alleviate this problem, we propose two approaches which are combined to create IDAAC: Invariant Decoupled Advantage Actor-Critic. First, IDAAC decouples the optimization of the policy and value function, using separate networks to model them. Second, it introduces an auxiliary loss which encourages the representation to be invariant to task-irrelevant properties of the environment. IDAAC shows good generalization to unseen environments, achieving a new state-of-the-art on the Procgen benchmark and outperforming popular methods on DeepMind Control tasks with distractors. Our implementation is available at https://github.com/rraileanu/idaac.

The high dimensionality of images presents architecture and sampling-efficiency challenges for likelihood-based generative models. Previous approaches such as VQ-VAE use deep autoencoders to obtain compact representations, which are more practical as inputs for likelihood-based models. We present an alternative approach, inspired by common image compression methods like JPEG, and convert images to quantized discrete cosine transform (DCT) blocks, which are represented sparsely as a sequence of DCT channel, spatial location, and DCT coefficient triples. We propose a Transformer-based autoregressive architecture, which is trained to sequentially predict the conditional distribution of the next element in such sequences, and which scales effectively to high resolution images. On a range of image datasets, we demonstrate that our approach can generate high quality, diverse images, with sample metric scores competitive with state of the art methods. We additionally show that simple modifications to our method yield effective image colorization and super-resolution models.

Individuality is essential in human society. It induces the division of labor and thus improves the efficiency and productivity. Similarly, it should also be a key to multi-agent cooperation. Inspired by that individuality is of being an individual separate from others, we propose a simple yet efficient method for the emergence of individuality (EOI) in multi-agent reinforcement learning (MARL). EOI learns a probabilistic classifier that predicts a probability distribution over agents given their observation and gives each agent an intrinsic reward of being correctly predicted by the classifier. The intrinsic reward encourages the agents to visit their own familiar observations, and learning the classifier by such observations makes the intrinsic reward signals stronger and in turn makes the agents more identifiable. To further enhance the intrinsic reward and promote the emergence of individuality, two regularizers are proposed to increase the discriminability of the classifier. We implement EOI on top of popular MARL algorithms. Empirically, we show that EOI outperforms existing methods in a variety of multi-agent cooperative scenarios.

Multi-modal distributions are commonly used to model clustered data in statistical learning tasks. In this paper, we consider the Mixed Linear Regression (MLR) problem. We propose an optimal transport-based framework for MLR problems, Wasserstein Mixed Linear Regression (WMLR), which minimizes the Wasserstein distance between the learned and target mixture regression models. Through a model-based duality analysis, WMLR reduces the underlying MLR task to a nonconvex-concave minimax optimization problem, which can be provably solved to find a minimax stationary point by the Gradient Descent Ascent (GDA) algorithm. In the special case of mixtures of two linear regression models, we show that WMLR enjoys global convergence and generalization guarantees. We prove that WMLR’s sample complexity grows linearly with the dimension of data. Finally, we discuss the application of WMLR to the federated learning task where the training samples are collected by multiple agents in a network. Unlike the Expectation-Maximization algorithm, WMLR directly extends to the distributed, federated learning setting. We support our theoretical results through several numerical experiments, which highlight our framework’s ability to handle the federated learning setting with mixture models.

Efficient evaluation of a network architecture drawn from a large search space remains a key challenge in Neural Architecture Search (NAS). Vanilla NAS evaluates each architecture by training from scratch, which gives the true performance but is extremely time-consuming. Recently, one-shot NAS substantially reduces the computation cost by training only one supernetwork, a.k.a. supernet, to approximate the performance of every architecture in the search space via weight-sharing. However, the performance estimation can be very inaccurate due to the co-adaption among operations. In this paper, we propose few-shot NAS that uses multiple supernetworks, called sub-supernet, each covering different regions of the search space to alleviate the undesired co-adaption. Compared to one-shot NAS, few-shot NAS improves the accuracy of architecture evaluation with a small increase of evaluation cost. With only up to 7 sub-supernets, few-shot NAS establishes new SoTAs: on ImageNet, it finds models that reach 80.5% top-1 accuracy at 600 MB FLOPS and 77.5% top-1 accuracy at 238 MFLOPS; on CIFAR10, it reaches 98.72% top-1 accuracy without using extra data or transfer learning. In Auto-GAN, few-shot NAS outperforms the previously published results by up to 20%. Extensive experiments show that few-shot NAS significantly improves various one-shot methods, including 4 gradient-based and …

Standard training via empirical risk minimization (ERM) can produce models that achieve low error on average but high error on minority groups, especially in the presence of spurious correlations between the input and label. Prior approaches to this problem, like group distributionally robust optimization (group DRO), generally require group annotations for every training point. On the other hand, approaches that do not use group annotations generally do not improve minority performance. For example, we find that joint DRO, which dynamically upweights examples with high training loss, tends to optimize for examples that are irrelevant to the specific groups we seek to do well on. In this paper, we propose a simple two-stage approach, JTT, that achieves comparable performance to group DRO while only requiring group annotations on a significantly smaller validation set. JTT first attempts to identify informative training examples, which are often minority examples, by training an initial ERM classifier and selecting the examples with high training loss. Then, it trains a final classifier by upsampling the selected examples. Crucially, unlike joint DRO, JTT does not iteratively upsample examples that have high loss under the final classifier. On four image classification and natural language processing tasks with spurious correlations, …

Weight-sharing neural architecture search (NAS) is an effective technique for automating efficient neural architecture design. Weight-sharing NAS builds a supernet that assembles all the architectures as its sub-networks and jointly trains the supernet with the sub-networks. The success of weight-sharing NAS heavily relies on distilling the knowledge of the supernet to the sub-networks. However, we find that the widely used distillation divergence, i.e., KL divergence, may lead to student sub-networks that over-estimate or under-estimate the uncertainty of the teacher supernet, leading to inferior performance of the sub-networks. In this work, we propose to improve the supernet training with a more generalized alpha-divergence. By adaptively selecting the alpha-divergence, we simultaneously prevent the over-estimation or under-estimation of the uncertainty of the teacher model. We apply the proposed alpha-divergence based supernets training to both slimmable neural networks and weight-sharing NAS, and demonstrate significant improvements. Specifically, our discovered model family, AlphaNet, outperforms prior-art models on a wide range of FLOPs regimes, including BigNAS, Once-for-All networks, and AttentiveNAS. We achieve ImageNet top-1 accuracy of 80.0% with only 444M FLOPs. Our code and pretrained models are available at https://github.com/facebookresearch/AlphaNet.

Decision analysis deals with modeling and enhancing decision processes. A principal challenge in improving behavior is in obtaining a transparent *description* of existing behavior in the first place. In this paper, we develop an expressive, unifying perspective on *inverse decision modeling*: a framework for learning parameterized representations of sequential decision behavior. First, we formalize the *forward* problem (as a normative standard), subsuming common classes of control behavior. Second, we use this to formalize the *inverse* problem (as a descriptive model), generalizing existing work on imitation/reward learning---while opening up a much broader class of research problems in behavior representation. Finally, we instantiate this approach with an example (*inverse bounded rational control*), illustrating how this structure enables learning (interpretable) representations of (bounded) rationality---while naturally capturing intuitive notions of suboptimal actions, biased beliefs, and imperfect knowledge of environments.

We address the issue of tuning hyperparameters (HPs) for imitation learning algorithms in the context of continuous-control, when the underlying reward function of the demonstrating expert cannot be observed at any time. The vast literature in imitation learning mostly considers this reward function to be available for HP selection, but this is not a realistic setting. Indeed, would this reward function be available, it could then directly be used for policy training and imitation would not be necessary. To tackle this mostly ignored problem, we propose a number of possible proxies to the external reward. We evaluate them in an extensive empirical study (more than 10'000 agents across 9 environments) and make practical recommendations for selecting HPs. Our results show that while imitation learning algorithms are sensitive to HP choices, it is often possible to select good enough HPs through a proxy to the reward function.

The increasing size of neural network models has been critical for improvements in their accuracy, but device memory is not growing at the same rate. This creates fundamental challenges for training neural networks within limited memory environments. In this work, we propose ActNN, a memory-efficient training framework that stores randomly quantized activations for back propagation. We prove the convergence of ActNN for general network architectures, and we characterize the impact of quantization on the convergence via an exact expression for the gradient variance. Using our theory, we propose novel mixed-precision quantization strategies that exploit the activation's heterogeneity across feature dimensions, samples, and layers. These techniques can be readily applied to existing dynamic graph frameworks, such as PyTorch, simply by substituting the layers. We evaluate ActNN on mainstream computer vision models for classification, detection, and segmentation tasks. On all these tasks, ActNN compresses the activation to 2 bits on average, with negligible accuracy loss. ActNN reduces the memory footprint of the activation by 12x, and it enables training with a 6.6x to 14x larger batch size.

Distributional shift is one of the major obstacles when transferring machine learning prediction systems from the lab to the real world. To tackle this problem, we assume that variation across training domains is representative of the variation we might encounter at test time, but also that shifts at test time may be more extreme in magnitude. In particular, we show that reducing differences in risk across training domains can reduce a model’s sensitivity to a wide range of extreme distributional shifts, including the challenging setting where the input contains both causal and anti-causal elements. We motivate this approach, Risk Extrapolation (REx), as a form of robust optimization over a perturbation set of extrapolated domains (MM-REx), and propose a penalty on the variance of training risks (V-REx) as a simpler variant. We prove that variants of REx can recover the causal mechanisms of the targets, while also providing robustness to changes in the input distribution (``covariate shift''). By appropriately trading-off robustness to causally induced distributional shifts and covariate shift, REx is able to outperform alternative methods such as Invariant Risk Minimization in situations where these types of shift co-occur.

Exploration is critical for good results in deep reinforcement learning and has attracted much attention. However, existing multi-agent deep reinforcement learning algorithms still use mostly noise-based techniques. Very recently, exploration methods that consider cooperation among multiple agents have been developed. However, existing methods suffer from a common challenge: agents struggle to identify states that are worth exploring, and hardly coordinate exploration efforts toward those states. To address this shortcoming, in this paper, we propose cooperative multi-agent exploration (CMAE): agents share a common goal while exploring. The goal is selected from multiple projected state spaces by a normalized entropy-based technique. Then, agents are trained to reach the goal in a coordinated manner. We demonstrate that CMAE consistently outperforms baselines on various tasks, including a sparse-reward version of multiple-particle environment (MPE) and the Starcraft multi-agent challenge (SMAC).

Least squares estimators, when trained on few target domain samples, may predict poorly. Supervised domain adaptation aims to improve the predictive accuracy by exploiting additional labeled training samples from a source distribution that is close to the target distribution. Given available data, we investigate novel strategies to synthesize a family of least squares estimator experts that are robust with regard to moment conditions. When these moment conditions are specified using Kullback-Leibler or Wasserstein-type divergences, we can find the robust estimators efficiently using convex optimization. We use the Bernstein online aggregation algorithm on the proposed family of robust experts to generate predictions for the sequential stream of target test samples. Numerical experiments on real data show that the robust strategies systematically outperform non-robust interpolations of the empirical least squares estimators.

We introduce a new unsupervised pretraining objective for reinforcement learning. During the unsupervised reward-free pretraining phase, the agent maximizes mutual information between tasks and states induced by the policy. Our key contribution is a novel lower bound of this intractable quantity. We show that by reinterpreting and combining variational successor features~\citep{Hansen2020Fast} with nonparametric entropy maximization~\citep{liu2021behavior}, the intractable mutual information can be efficiently optimized. The proposed method Active Pretraining with Successor Feature (APS) explores the environment via nonparametric entropy maximization, and the explored data can be efficiently leveraged to learn behavior by variational successor features. APS addresses the limitations of existing mutual information maximization based and entropy maximization based unsupervised RL, and combines the best of both worlds. When evaluated on the Atari 100k data-efficiency benchmark, our approach significantly outperforms previous methods combining unsupervised pretraining with task-specific finetuning.

Latent variable models have been successfully applied in lossless compression with the bits-back coding algorithm. However, bits-back suffers from an increase in the bitrate equal to the KL divergence between the approximate posterior and the true posterior. In this paper, we show how to remove this gap asymptotically by deriving bits-back coding algorithms from tighter variational bounds. The key idea is to exploit extended space representations of Monte Carlo estimators of the marginal likelihood. Naively applied, our schemes would require more initial bits than the standard bits-back coder, but we show how to drastically reduce this additional cost with couplings in the latent space. When parallel architectures can be exploited, our coders can achieve better rates than bits-back with little additional cost. We demonstrate improved lossless compression rates in a variety of settings, especially in out-of-distribution or sequential data compression.

Solving optimization tasks based on functions and losses with a topological flavor is a very active and growing field of research in data science and Topological Data Analysis, with applications in non-convex optimization, statistics and machine learning. However, the approaches proposed in the literature are usually anchored to a specific application and/or topological construction, and do not come with theoretical guarantees. To address this issue, we study the differentiability of a general map associated with the most common topological construction, that is, the persistence map. Building on real analytic geometry arguments, we propose a general framework that allows us to define and compute gradients for persistence-based functions in a very simple way. We also provide a simple, explicit and sufficient condition for convergence of stochastic subgradient methods for such functions. This result encompasses all the constructions and applications of topological optimization in the literature. Finally, we provide associated code, that is easy to handle and to mix with other non-topological methods and constraints, as well as some experiments showcasing the versatility of our approach.

Energy-based models (EBMs) are a simple yet powerful framework for generative modeling. They are based on a trainable energy function which defines an associated Gibbs measure, and they can be trained and sampled from via well-established statistical tools, such as MCMC. Neural networks may be used as energy function approximators, providing both a rich class of expressive models as well as a flexible device to incorporate data structure. In this work we focus on shallow neural networks. Building from the incipient theory of overparametrized neural networks, we show that models trained in the so-called 'active' regime provide a statistical advantage over their associated 'lazy' or kernel regime, leading to improved adaptivity to hidden low-dimensional structure in the data distribution, as already observed in supervised learning. Our study covers both the maximum likelihood and Stein Discrepancy estimators, and we validate our theoretical results with numerical experiments on synthetic data.

Compared to minimization, the min-max optimization in machine learning applications is considerably more convoluted because of the existence of cycles and similar phenomena. Such oscillatory behaviors are well-understood in the convex-concave regime, and many algorithms are known to overcome them. In this paper, we go beyond this basic setting and characterize the convergence properties of many popular methods in solving non-convex/non-concave problems. In particular, we show that a wide class of state-of-the-art schemes and heuristics may converge with arbitrarily high probability to attractors that are in no way min-max optimal or even stationary. Our work thus points out a potential pitfall among many existing theoretical frameworks, and we corroborate our theoretical claims by explicitly showcasing spurious attractors in simple two-dimensional problems.

Imitation learning seeks to circumvent the difficulty in designing proper reward functions for training agents by utilizing expert behavior. With environments modeled as Markov Decision Processes (MDP), most of the existing imitation algorithms are contingent on the availability of expert demonstrations in the same MDP as the one in which a new imitation policy is to be learned. In this paper, we study the problem of how to imitate tasks when discrepancies exist between the expert and agent MDP. These discrepancies across domains could include differing dynamics, viewpoint, or morphology; we present a novel framework to learn correspondences across such domains. Importantly, in contrast to prior works, we use unpaired and unaligned trajectories containing only states in the expert domain, to learn this correspondence. We utilize a cycle-consistency constraint on both the state space and a domain agnostic latent space to do this. In addition, we enforce consistency on the temporal position of states via a normalized position estimator function, to align the trajectories across the two domains. Once this correspondence is found, we can directly transfer the demonstrations on one domain to the other and use it for imitation. Experiments across a wide variety of challenging domains demonstrate the …

The display advertising industry has recently transitioned from second- to first-price auctions as its primary mechanism for ad allocation and pricing. In light of this, publishers need to re-evaluate and optimize their auction parameters, notably reserve prices. In this paper, we propose a gradient-based algorithm to adaptively update and optimize reserve prices based on estimates of bidders' responsiveness to experimental shocks in reserves. Our key innovation is to draw on the inherent structure of the revenue objective in order to reduce the variance of gradient estimates and improve convergence rates in both theory and practice. We show that revenue in a first-price auction can be usefully decomposed into a \emph{demand} component and a \emph{bidding} component, and introduce techniques to reduce the variance of each component. We characterize the bias-variance trade-offs of these techniques and validate the performance of our proposed algorithm through experiments on synthetic data and real display ad auctions data from a major ad exchange.

This paper aims to provide understandings for the effect of an over-parameterized model, e.g. a deep neural network, memorizing instance-dependent noisy labels. We first quantify the harms caused by memorizing noisy instances, and show the disparate impacts of noisy labels for sample instances with different representation frequencies. We then analyze how several popular solutions for learning with noisy labels mitigate this harm at the instance level. Our analysis reveals that existing approaches lead to disparate treatments when handling noisy instances. While higher-frequency instances often enjoy a high probability of an improvement by applying these solutions, lower-frequency instances do not. Our analysis reveals new understandings for when these approaches work, and provides theoretical justifications for previously reported empirical observations. This observation requires us to rethink the distribution of label noise across instances and calls for different treatments for instances in different regimes.

This work introduces Bilinear Classes, a new structural framework, which permit generalization in reinforcement learning in a wide variety of settings through the use of function approximation. The framework incorporates nearly all existing models in which a polynomial sample complexity is achievable, and, notably, also includes new models, such as the Linear Q*/V* model in which both the optimal Q-function and the optimal V-function are linear in some known feature space. Our main result provides an RL algorithm which has polynomial sample complexity for Bilinear Classes; notably, this sample complexity is stated in terms of a reduction to the generalization error of an underlying supervised learning sub-problem. These bounds nearly match the best known sample complexity bounds for existing models. Furthermore, this framework also extends to the infinite dimensional (RKHS) setting: for the the Linear Q*/V* model, linear MDPs, and linear mixture MDPs, we provide sample complexities that have no explicit dependence on the explicit feature dimension (which could be infinite), but instead depends only on information theoretic quantities.

We analyze the properties of gradient descent on convex surrogates for the zero-one loss for the agnostic learning of halfspaces. We show that when a quantity we refer to as the \textit{soft margin} is well-behaved---a condition satisfied by log-concave isotropic distributions among others---minimizers of convex surrogates for the zero-one loss are approximate minimizers for the zero-one loss itself. As standard convex optimization arguments lead to efficient guarantees for minimizing convex surrogates of the zero-one loss, our methods allow for the first positive guarantees for the classification error of halfspaces learned by gradient descent using the binary cross-entropy or hinge loss in the presence of agnostic label noise.

The connection between training deep neural networks (DNNs) and optimal control theory (OCT) has attracted considerable attention as a principled tool of algorithmic design. Despite few attempts being made, they have been limited to architectures where the layer propagation resembles a Markovian dynamical system. This casts doubts on their flexibility to modern networks that heavily rely on non-Markovian dependencies between layers (e.g. skip connections in residual networks). In this work, we propose a novel dynamic game perspective by viewing each layer as a player in a dynamic game characterized by the DNN itself. Through this lens, different classes of optimizers can be seen as matching different types of Nash equilibria, depending on the implicit information structure of each (p)layer. The resulting method, called Dynamic Game Theoretic Neural Optimizer (DGNOpt), not only generalizes OCT-inspired optimizers to richer network class; it also motivates a new training principle by solving a multi-player cooperative game. DGNOpt shows convergence improvements over existing methods on image classification datasets with residual and inception networks. Our work marries strengths from both OCT and game theory, paving ways to new algorithmic opportunities from robust optimal control and bandit-based optimization.

The study of strategic or adversarial manipulation of testing data to fool a classifier has attracted much recent attention. Most previous works have focused on two extreme situations where any testing data point either is completely adversarial or always equally prefers the positive label. In this paper, we generalize both of these through a unified framework for strategic classification and introduce the notion of strategic VC-dimension (SVC) to capture the PAC-learnability in our general strategic setup. SVC provably generalizes the recent concept of adversarial VC-dimension (AVC) introduced by Cullina et al. (2018). We instantiate our framework for the fundamental strategic linear classification problem. We fully characterize: (1) the statistical learnability of linear classifiers by pinning down its SVC; (2) it's computational tractability by pinning down the complexity of the empirical risk minimization problem. Interestingly, the SVC of linear classifiers is always upper bounded by its standard VC-dimension. This characterization also strictly generalizes the AVC bound for linear classifiers in (Cullina et al., 2018).

Learning composable policies for environments with complex rules and tasks is a challenging problem. We introduce a hierarchical reinforcement learning framework called the Logical Options Framework (LOF) that learns policies that are satisfying, optimal, and composable. LOF efficiently learns policies that satisfy tasks by representing the task as an automaton and integrating it into learning and planning. We provide and prove conditions under which LOF will learn satisfying, optimal policies. And lastly, we show how LOF's learned policies can be composed to satisfy unseen tasks with only 10-50 retraining steps on our benchmarks. We evaluate LOF on four tasks in discrete and continuous domains, including a 3D pick-and-place environment.

In recent years methods from optimal linear experimental design have been leveraged to obtain state of the art results for linear bandits.
A design returned from an objective such as G-optimal design is actually a probability distribution over a pool of potential measurement vectors.
Consequently, one nuisance of the approach is the task of converting this continuous probability distribution into a discrete assignment of N measurements.
While sophisticated rounding techniques have been proposed, in d dimensions they require N to be at least d, d log(log(d)), or d^2 based on the sub-optimality of the solution.
In this paper we are interested in settings where N may be much less than d, such as in experimental design in an RKHS where d may be effectively infinite.

In this work, we propose a rounding procedure that frees N of any dependence on the dimension d, while achieving nearly the same performance guarantees of existing rounding procedures.
We evaluate the procedure against a baseline that projects the problem to a lower dimensional space and performs rounding there, which requires N to just be at least a notion of the effective dimension. We also leverage our new approach in a new algorithm for kernelized …

An important problem in systems neuroscience is to identify the latent dynamics underlying neural population activity. Here we address this problem by introducing a low-dimensional nonlinear model for latent neural population dynamics using neural ordinary differential equations (neural ODEs), with noisy sensory inputs and Poisson spike train outputs. We refer to this as the Poisson Latent Neural Differential Equations (PLNDE) model. We apply the PLNDE framework to a variety of synthetic datasets, and show that it accurately infers the phase portraits and fixed points of nonlinear systems augmented to produce spike train data, including the FitzHugh-Nagumo oscillator, a 3-dimensional nonlinear spiral, and a nonlinear sensory decision-making model with attractor dynamics. Our model significantly outperforms existing methods at inferring single-trial neural firing rates and the corresponding latent trajectories that generated them, especially in the regime where the spike counts and number of trials are low. We then apply our model to multi-region neural population recordings from medial frontal cortex of rats performing an auditory decision-making task. Our model provides a general, interpretable framework for investigating the neural mechanisms of decision-making and other cognitive computations through the lens of dynamical systems.

Recent work has highlighted the role of initialization scale in determining the structure of the solutions that gradient methods converge to. In particular, it was shown that large initialization leads to the neural tangent kernel regime solution, whereas small initialization leads to so called ``rich regimes''. However, the initialization structure is richer than the overall scale alone and involves relative magnitudes of different weights and layers in the network. Here we show that these relative scales, which we refer to as initialization shape, play an important role in determining the learned model. We develop a novel technique for deriving the inductive bias of gradient-flow and use it to obtain closed-form implicit regularizers for multiple cases of interest.

Sequential data with serial correlation and an unknown, unstructured, and dynamic background is ubiquitous in neuroscience, psychology, and econometrics. Inferring serial correlation for such data is a fundamental challenge in statistics. We propose a Total Variation (TV) constrained least square estimator coupled with hypothesis tests to infer the serial correlation in the presence of unknown and unstructured dynamic background. The TV constraint on the dynamic background encourages a piecewise constant structure, which can approximate a wide range of dynamic backgrounds. The tuning parameter is selected via the Ljung-Box test to control the bias-variance trade-off. We establish a non-asymptotic upper bound for the estimation error through variational inequalities. We also derive a lower error bound via Fano's method and show the proposed method is near-optimal. Numerical simulation and a real study in psychology demonstrate the excellent performance of our proposed method compared with the state-of-the-art.

Deep neural networks give state-of-the-art accuracy for reconstructing images from few and noisy measurements, a problem arising for example in accelerated magnetic resonance imaging (MRI). However, recent works have raised concerns that deep-learning-based image reconstruction methods are sensitive to perturbations and are less robust than traditional methods: Neural networks (i) may be sensitive to small, yet adversarially-selected perturbations, (ii) may perform poorly under distribution shifts, and (iii) may fail to recover small but important features in an image. In order to understand the sensitivity to such perturbations, in this work, we measure the robustness of different approaches for image reconstruction including trained and un-trained neural networks as well as traditional sparsity-based methods. We find, contrary to prior works, that both trained and un-trained methods are vulnerable to adversarial perturbations. Moreover, both trained and un-trained methods tuned for a particular dataset suffer very similarly from distribution shifts. Finally, we demonstrate that an image reconstruction method that achieves higher reconstruction quality, also performs better in terms of accurately recovering fine details. Our results indicate that the state-of-the-art deep-learning-based image reconstruction methods provide improved performance than traditional methods without compromising robustness.

Promoting behavioural diversity is critical for solving games with non-transitive dynamics where strategic cycles exist, and there is no consistent winner (e.g., Rock-Paper-Scissors). Yet, there is a lack of rigorous treatment for defining diversity and constructing diversity-aware learning dynamics. In this work, we offer a geometric interpretation of behavioural diversity in games and introduce a novel diversity metric based on \emph{determinantal point processes} (DPP). By incorporating the diversity metric into best-response dynamics, we develop \emph{diverse fictitious play} and \emph{diverse policy-space response oracle} for solving normal-form games and open-ended games. We prove the uniqueness of the diverse best response and the convergence of our algorithms on two-player games. Importantly, we show that maximising the DPP-based diversity metric guarantees to enlarge the \emph{gamescape} -- convex polytopes spanned by agents' mixtures of strategies. To validate our diversity-aware solvers, we test on tens of games that show strong non-transitivity. Results suggest that our methods achieve at least the same, and in most games, lower exploitability than PSRO solvers by finding effective and diverse strategies.

Several practical applications of reinforcement learning involve an agent learning from past data without the possibility of further exploration. Often these applications require us to 1) identify a near optimal policy or to 2) estimate the value of a target policy. For both tasks we derive exponential information-theoretic lower bounds in discounted infinite horizon MDPs with a linear function representation for the action value function even if 1) realizability holds, 2) the batch algorithm observes the exact reward and transition functions, and 3) the batch algorithm is given the best a priori data distribution for the problem class. Our work introduces a new `oracle + batch algorithm' framework to prove lower bounds that hold for every distribution. The work shows an exponential separation between batch and online reinforcement learning.

Despite their overwhelming capacity to overfit, deep neural networks trained by specific optimization algorithms tend to generalize relatively well to unseen data. Recently, researchers explained it by investigating the implicit bias of optimization algorithms. A remarkable progress is the work (Lyu & Li, 2019), which proves gradient descent (GD) maximizes the margin of homogeneous deep neural networks. Except the first-order optimization algorithms like GD, adaptive algorithms such as AdaGrad, RMSProp and Adam are popular owing to their rapid training process. Mean-while, numerous works have provided empirical evidence that adaptive methods may suffer from poor generalization performance. However, theoretical explanation for the generalization of adaptive optimization algorithms is still lacking. In this paper, we study the implicit bias of adaptive optimization algorithms on homogeneous neural networks. In particular, we study the convergent direction of parameters when they are optimizing the logistic loss. We prove that the convergent direction of Adam and RMSProp is the same as GD, while for AdaGrad, the convergent direction depends on the adaptive conditioner. Technically, we provide a unified framework to analyze convergent direction of adaptive optimization algorithms by constructing novel and nontrivial adaptive gradient flow and surrogate margin. The theoretical findings explain the superiority on generalization …

Although Label Distribution Learning (LDL) has witnessed extensive classification applications, it faces the challenge of objective mismatch -- the objective of LDL mismatches that of classification, which has seldom been noticed in existing studies. Our goal is to solve the objective mismatch and improve the classification performance of LDL. Specifically, we extend the margin theory to LDL and propose a new LDL method called \textbf{L}abel \textbf{D}istribution \textbf{L}earning \textbf{M}achine (LDLM). First, we define the label distribution margin and propose the \textbf{S}upport \textbf{V}ector \textbf{R}egression \textbf{M}achine (SVRM) to learn the optimal label. Second, we propose the adaptive margin loss to learn label description degrees. In theoretical analysis, we develop a generalization theory for the SVRM and analyze the generalization of LDLM. Experimental results validate the better classification performance of LDLM.

In single-item auction design, it is well known due to Cremer and McLean that when bidders’ valuations are drawn from a correlated prior distribution, the auctioneer can extract full social surplus as revenue. However, in most real-world applications, the prior is usually unknown and can only be learned from historical data. In this work, we investigate the robustness of the optimal auction with correlated valuations via sample complexity analysis. We prove upper and lower bounds on the number of samples from the unknown prior required to learn a (1-epsilon)-approximately optimal auction. Our results reinforce the common belief that optimal correlated auctions are sensitive to the distribution parameters and hard to learn unless the prior distribution is well-behaved.

Exploration in unknown environments is a fundamental problem in reinforcement learning and control. In this work, we study task-guided exploration and determine what precisely an agent must learn about their environment in order to complete a particular task. Formally, we study a broad class of decision-making problems in the setting of linear dynamical systems, a class that includes the linear quadratic regulator problem. We provide instance- and task-dependent lower bounds which explicitly quantify the difficulty of completing a task of interest. Motivated by our lower bound, we propose a computationally efficient experiment-design based exploration algorithm. We show that it optimally explores the environment, collecting precisely the information needed to complete the task, and provide finite-time bounds guaranteeing that it achieves the instance- and task-optimal sample complexity, up to constant factors. Through several examples of the linear quadratic regulator problem, we show that performing task-guided exploration provably improves on exploration schemes which do not take into account the task of interest. Along the way, we establish that certainty equivalence decision making is instance- and task-optimal, and obtain the first algorithm for the linear quadratic regulator problem which is instance-optimal. We conclude with several experiments illustrating the effectiveness of our approach in …

We study exploration in stochastic multi-armed bandits when we have access to a divisible resource that can be allocated in varying amounts to arm pulls. We focus in particular on the allocation of distributed computing resources, where we may obtain results faster by allocating more resources per pull, but might have reduced throughput due to nonlinear scaling. For example, in simulation-based scientific studies, an expensive simulation can be sped up by running it on multiple cores. This speed-up however, is partly offset by the communication among cores, which results in lower throughput than if fewer cores were allocated to run more trials in parallel. In this paper, we explore these trade-offs in two settings. First, in a fixed confidence setting, we need to find the best arm with a given target success probability as quickly as possible. We propose an algorithm which trades off between information accumulation and throughput and show that the time taken can be upper bounded by the solution of a dynamic program whose inputs are the gaps between the sub-optimal and optimal arms. We also prove a matching hardness result. Second, we present an algorithm for a fixed deadline setting, where we are given a time …

To assess generalization, machine learning scientists typically either (i) bound the generalization gap and then (after training) plug in the empirical risk to obtain a bound on the true risk; or (ii) validate empirically on holdout data. However, (i) typically yields vacuous guarantees for overparameterized models; and (ii) shrinks the training set and its guarantee erodes with each re-use of the holdout set. In this paper, we leverage unlabeled data to produce generalization bounds. After augmenting our (labeled) training set with randomly labeled data, we train in the standard fashion. Whenever classifiers achieve low error on the clean data but high error on the random data, our bound ensures that the true risk is low. We prove that our bound is valid for 0-1 empirical risk minimization and with linear classifiers trained by gradient descent. Our approach is especially useful in conjunction with deep learning due to the early learning phenomenon whereby networks fit true labels before noisy labels but requires one intuitive assumption. Empirically, on canonical computer vision and NLP tasks, our bound provides non-vacuous generalization guarantees that track actual performance closely. This work enables practitioners to certify generalization even when (labeled) holdout data is unavailable and provides insights …

We study multi-objective reinforcement learning (RL) where an agent's reward is represented as a vector. In settings where an agent competes against opponents, its performance is measured by the distance of its average return vector to a target set. We develop statistically and computationally efficient algorithms to approach the associated target set. Our results extend Blackwell's approachability theorem~\citep{blackwell1956analog} to tabular RL, where strategic exploration becomes essential. The algorithms presented are adaptive; their guarantees hold even without Blackwell's approachability condition. If the opponents use fixed policies, we give an improved rate of approaching the target set while also tackling the more ambitious goal of simultaneously minimizing a scalar cost function. We discuss our analysis for this special case by relating our results to previous works on constrained RL. To our knowledge, this work provides the first provably efficient algorithms for vector-valued Markov games and our theoretical guarantees are near-optimal.

Many machine learning problems can be formulated as minimax problems such as Generative Adversarial Networks (GANs), AUC maximization and robust estimation, to mention but a few. A substantial amount of studies are devoted to studying the convergence behavior of their stochastic gradient-type algorithms. In contrast, there is relatively little work on understanding their generalization, i.e., how the learning models built from training examples would behave on test examples. In this paper, we provide a comprehensive generalization analysis of stochastic gradient methods for minimax problems under both convex-concave and nonconvex-nonconcave cases through the lens of algorithmic stability. We establish a quantitative connection between stability and several generalization measures both in expectation and with high probability. For the convex-concave setting, our stability analysis shows that stochastic gradient descent ascent attains optimal generalization bounds for both smooth and nonsmooth minimax problems. We also establish generalization bounds for both weakly-convex-weakly-concave and gradient-dominated problems. We report preliminary experimental results to verify our theory.

Minimizing cross-entropy over the softmax scores of a linear map composed with a high-capacity encoder is arguably the most popular choice for training neural networks on supervised learning tasks. However, recent works show that one can directly optimize the encoder instead, to obtain equally (or even more) discriminative representations via a supervised variant of a contrastive objective. In this work, we address the question whether there are fundamental differences in the sought-for representation geometry in the output space of the encoder at minimal loss. Specifically, we prove, under mild assumptions, that both losses attain their minimum once the representations of each class collapse to the vertices of a regular simplex, inscribed in a hypersphere. We provide empirical evidence that this configuration is attained in practice and that reaching a close-to-optimal state typically indicates good generalization performance. Yet, the two losses show remarkably different optimization behavior. The number of iterations required to perfectly fit to data scales superlinearly with the amount of randomly flipped labels for the supervised contrastive loss. This is in contrast to the approximately linear scaling previously reported for networks trained with cross-entropy.

We develop a method to construct distribution-free prediction intervals for dynamic time-series, called \Verb|EnbPI| that wraps around any bootstrap ensemble estimator to construct sequential prediction intervals. \Verb|EnbPI| is closely related to the conformal prediction (CP) framework but does not require data exchangeability. Theoretically, these intervals attain finite-sample, \textit{approximately valid} marginal coverage for broad classes of regression functions and time-series with strongly mixing stochastic errors. Computationally, \Verb|EnbPI| avoids overfitting and requires neither data-splitting nor training multiple ensemble estimators; it efficiently aggregates bootstrap estimators that have been trained. In general, \Verb|EnbPI| is easy to implement, scalable to producing arbitrarily many prediction intervals sequentially, and well-suited to a wide range of regression functions. We perform extensive real-data analyses to demonstrate its effectiveness.

Spatio-temporal forecasting has numerous applications in analyzing wireless, traffic, and financial networks. Many classical statistical models often fall short in handling the complexity and high non-linearity present in time-series data. Recent advances in deep learning allow for better modelling of spatial and temporal dependencies. While most of these models focus on obtaining accurate point forecasts, they do not characterize the prediction uncertainty. In this work, we consider the time-series data as a random realization from a nonlinear state-space model and target Bayesian inference of the hidden states for probabilistic forecasting. We use particle flow as the tool for approximating the posterior distribution of the states, as it is shown to be highly effective in complex, high-dimensional settings. Thorough experimentation on several real world time-series datasets demonstrates that our approach provides better characterization of uncertainty while maintaining comparable accuracy to the state-of-the-art point forecasting methods.

We consider repair tasks: given a critic (e.g., compiler) that assesses the quality of an input, the goal is to train a fixer that converts a bad example (e.g., code with syntax errors) into a good one (e.g., code with no errors). Existing works create training data consisting of (bad, good) pairs by corrupting good examples using heuristics (e.g., dropping tokens). However, fixers trained on this synthetically-generated data do not extrapolate well to the real distribution of bad inputs. To bridge this gap, we propose a new training approach, Break-It-Fix-It (BIFI), which has two key ideas: (i) we use the critic to check a fixer's output on real bad inputs and add good (fixed) outputs to the training data, and (ii) we train a breaker to generate realistic bad code from good code. Based on these ideas, we iteratively update the breaker and the fixer while using them in conjunction to generate more paired data. We evaluate BIFI on two code repair datasets: GitHub-Python, a new dataset we introduce where the goal is to repair Python code with AST parse errors; and DeepFix, where the goal is to repair C code with compiler errors. BIFI outperforms existing methods, obtaining 90.5% …

We study a fundamental problem in computational chemistry known as molecular conformation generation, trying to predict stable 3D structures from 2D molecular graphs. Existing machine learning approaches usually first predict distances between atoms and then generate a 3D structure satisfying the distances, where noise in predicted distances may induce extra errors during 3D coordinate generation. Inspired by the traditional force field methods for molecular dynamics simulation, in this paper, we propose a novel approach called ConfGF by directly estimating the gradient fields of the log density of atomic coordinates. The estimated gradient fields allow directly generating stable conformations via Langevin dynamics. However, the problem is very challenging as the gradient fields are roto-translation equivariant. We notice that estimating the gradient fields of atomic coordinates can be translated to estimating the gradient fields of interatomic distances, and hence develop a novel algorithm based on recent score-based generative models to effectively estimate these gradients. Experimental results across multiple tasks show that ConfGF outperforms previous state-of-the-art baselines by a significant margin.

Can models with particular structure avoid being biased towards spurious correlation in out-of-distribution (OOD) generalization? Peters et al. (2016) provides a positive answer for linear cases. In this paper, we use a functional modular probing method to analyze deep model structures under OOD setting. We demonstrate that even in biased models (which focus on spurious correlation) there still exist unbiased functional subnetworks. Furthermore, we articulate and confirm the functional lottery ticket hypothesis: the full network contains a subnetwork with proper structure that can achieve better OOD performance. We then propose Modular Risk Minimization to solve the subnetwork selection problem. Our algorithm learns the functional structure from a given dataset, and can be combined with any other OOD regularization methods. Experiments on various OOD generalization tasks corroborate the effectiveness of our method.

In multi-dimensional classification (MDC), there are multiple class variables in the output space with each of them corresponding to one heterogeneous class space. Due to the heterogeneity of class spaces, it is quite challenging to consider the dependencies among class variables when learning from MDC examples. In this paper, we propose a novel MDC approach named SLEM which learns the predictive model in an encoded label space instead of the original heterogeneous one. Specifically, SLEM works in an encoding-training-decoding framework. In the encoding phase, each class vector is mapped into a real-valued one via three cascaded operations including pairwise grouping, one-hot conversion and sparse linear encoding. In the training phase, a multi-output regression model is learned within the encoded label space. In the decoding phase, the predicted class vector is obtained by adapting orthogonal matching pursuit over outputs of the learned multi-output regression model. Experimental results clearly validate the superiority of SLEM against state-of-the-art MDC approaches.

A key problem in program synthesis is searching over the large space of possible programs. Human programmers might decide the high-level structure of the desired program before thinking about the details; motivated by this intuition, we consider two-level search for program synthesis, in which the synthesizer first generates a plan, a sequence of symbols that describes the desired program at a high level, before generating the program. We propose to learn representations of programs that can act as plans to organize such a two-level search. Discrete latent codes are appealing for this purpose, and can be learned by applying recent work on discrete autoencoders. Based on these insights, we introduce the Latent Programmer (LP), a program synthesis method that first predicts a discrete latent code from input/output examples, and then generates the program in the target language. We evaluate the LP on two domains, demonstrating that it yields an improvement in accuracy, especially on longer programs for which search is most difficult.

Pre-trained representations are becoming crucial for many NLP and perception tasks. While representation learning in NLP has transitioned to training on raw text without human annotations, visual and vision-language representations still rely heavily on curated training datasets that are expensive or require expert knowledge. For vision applications, representations are mostly learned using datasets with explicit class labels such as ImageNet or OpenImages. For vision-language, popular datasets like Conceptual Captions, MSCOCO, or CLIP all involve a non-trivial data collection (and cleaning) process. This costly curation process limits the size of datasets and hence hinders the scaling of trained models. In this paper, we leverage a noisy dataset of over one billion image alt-text pairs, obtained without expensive filtering or post-processing steps in the Conceptual Captions dataset. A simple dual-encoder architecture learns to align visual and language representations of the image and text pairs using a contrastive loss. We show that the scale of our corpus can make up for its noise and leads to state-of-the-art representations even with such a simple learning scheme. Our visual representation achieves strong performance when transferred to classification tasks such as ImageNet and VTAB. The aligned visual and language representations enables zero-shot image classification and also …

Selective classification is a powerful tool for decision-making in scenarios where mistakes are costly but abstentions are allowed. In general, by allowing a classifier to abstain, one can improve the performance of a model at the cost of reducing coverage and classifying fewer samples. However, recent work has shown, in some cases, that selective classification can magnify disparities between groups, and has illustrated this phenomenon on multiple real-world datasets. We prove that the sufficiency criterion can be used to mitigate these disparities by ensuring that selective classification increases performance on all groups, and introduce a method for mitigating the disparity in precision across the entire coverage scale based on this criterion. We then provide an upper bound on the conditional mutual information between the class label and sensitive attribute, conditioned on the learned features, which can be used as a regularizer to achieve fairer selective classification. The effectiveness of the method is demonstrated on the Adult, CelebA, Civil Comments, and CheXpert datasets.

Local graph clustering is an important algorithmic technique for analysing massive graphs, and has been widely applied in many research fields of data science. While the objective of most (local) graph clustering algorithms is to find a vertex set of low conductance, there has been a sequence of recent studies that highlight the importance of the inter-connection between clusters when analysing real-world datasets. Following this line of research, in this work we study local algorithms for finding a pair of vertex sets defined with respect to their inter-connection and their relationship with the rest of the graph. The key to our analysis is a new reduction technique that relates the structure of multiple sets to a single vertex set in the reduced graph. Among many potential applications, we show that our algorithms successfully recover densely connected clusters in the Interstate Disputes Dataset and the US Migration Dataset.

Particle Filtering (PF) methods are an established class of procedures for performing inference in non-linear state-space models. Resampling is a key ingredient of PF necessary to obtain low variance likelihood and states estimates. However, traditional resampling methods result in PF-based loss functions being non-differentiable with respect to model and PF parameters. In a variational inference context, resampling also yields high variance gradient estimates of the PF-based evidence lower bound. By leveraging optimal transport ideas, we introduce a principled differentiable particle filter and provide convergence results. We demonstrate this novel method on a variety of applications.

Inspired by a new coded computation algorithm for invertible functions, we propose Coded-InvNet a new approach to design resilient prediction serving systems that can gracefully handle stragglers or node failures. Coded-InvNet leverages recent findings in the deep learning literature such as invertible neural networks, Manifold Mixup, and domain translation algorithms, identifying interesting research directions that span across machine learning and systems. Our experimental results show that Coded-InvNet can outperform existing approaches, especially when the compute resource overhead is as low as 10%. For instance, without knowing which of the ten workers is going to fail, our algorithm can design a backup task so that it can correctly recover the missing prediction result with an accuracy of 85.9%, significantly outperforming the previous SOTA by 32.5%.

In learning with noisy labels, for every instance, its label can randomly walk to other classes following a transition distribution which is named a noise model. Well-studied noise models are all instance-independent, namely, the transition depends only on the original label but not the instance itself, and thus they are less practical in the wild. Fortunately, methods based on instance-dependent noise have been studied, but most of them have to rely on strong assumptions on the noise models. To alleviate this issue, we introduce confidence-scored instance-dependent noise (CSIDN), where each instance-label pair is equipped with a confidence score. We find that with the help of confidence scores, the transition distribution of each instance can be approximately estimated. Similarly to the powerful forward correction for instance-independent noise, we propose a novel instance-level forward correction for CSIDN. We demonstrate the utility and effectiveness of our method through multiple experiments on datasets with synthetic label noise and real-world unknown noise.

We propose a lower bound on the log marginal likelihood of Gaussian process regression models that can be computed without matrix factorisation of the full kernel matrix. We show that approximate maximum likelihood learning of model parameters by maximising our lower bound retains many benefits of the sparse variational approach while reducing the bias introduced into hyperparameter learning. The basis of our bound is a more careful analysis of the log-determinant term appearing in the log marginal likelihood, as well as using the method of conjugate gradients to derive tight lower bounds on the term involving a quadratic form. Our approach is a step forward in unifying methods relying on lower bound maximisation (e.g. variational methods) and iterative approaches based on conjugate gradients for training Gaussian processes. In experiments, we show improved predictive performance with our model for a comparable amount of training time compared to other conjugate gradient based approaches.

We show that learning can be improved by using loss functions that evolve cyclically during training to emphasize one class at a time. In underparameterized networks, such dynamical loss functions can lead to successful training for networks that fail to find deep minima of the standard cross-entropy loss. In overparameterized networks, dynamical loss functions can lead to better generalization. Improvement arises from the interplay of the changing loss landscape with the dynamics of the system as it evolves to minimize the loss. In particular, as the loss function oscillates, instabilities develop in the form of bifurcation cascades, which we study using the Hessian and Neural Tangent Kernel. Valleys in the landscape widen and deepen, and then narrow and rise as the loss landscape changes during a cycle. As the landscape narrows, the learning rate becomes too large and the network becomes unstable and bounces around the valley. This process ultimately pushes the system into deeper and wider regions of the loss landscape and is characterized by decreasing eigenvalues of the Hessian. This results in better regularized models with improved generalization performance.

Many transfer problems require re-using previously optimal decisions for solving new tasks, which suggests the need for learning algorithms that can modify the mechanisms for choosing certain actions independently of those for choosing others. However, there is currently no formalism nor theory for how to achieve this kind of modular credit assignment. To answer this question, we define modular credit assignment as a constraint on minimizing the algorithmic mutual information among feedback signals for different decisions. We introduce what we call the modularity criterion for testing whether a learning algorithm satisfies this constraint by performing causal analysis on the algorithm itself. We generalize the recently proposed societal decision-making framework as a more granular formalism than the Markov decision process to prove that for decision sequences that do not contain cycles, certain single-step temporal difference action-value methods meet this criterion while all policy-gradient methods do not. Empirical evidence suggests that such action-value methods are more sample efficient than policy-gradient methods on transfer problems that require only sparse changes to a sequence of previously optimal decisions.

Real-world data often exhibit imbalanced distributions, where certain target values have significantly fewer observations. Existing techniques for dealing with imbalanced data focus on targets with categorical indices, i.e., different classes. However, many tasks involve continuous targets, where hard boundaries between classes do not exist. We define Deep Imbalanced Regression (DIR) as learning from such imbalanced data with continuous targets, dealing with potential missing data for certain target values, and generalizing to the entire target range. Motivated by the intrinsic difference between categorical and continuous label space, we propose distribution smoothing for both labels and features, which explicitly acknowledges the effects of nearby targets, and calibrates both label and learned feature distributions. We curate and benchmark large-scale DIR datasets from common real-world tasks in computer vision, natural language processing, and healthcare domains. Extensive experiments verify the superior performance of our strategies. Our work fills the gap in benchmarks and techniques for practical imbalanced regression problems. Code and data are available at: https://github.com/YyzHarry/imbalanced-regression.

Many weakly supervised classification methods employ a noise transition matrix to capture the class-conditional label corruption. To estimate the transition matrix from noisy data, existing methods often need to estimate the noisy class-posterior, which could be unreliable due to the overconfidence of neural networks. In this work, we propose a theoretically grounded method that can estimate the noise transition matrix and learn a classifier simultaneously, without relying on the error-prone noisy class-posterior estimation. Concretely, inspired by the characteristics of the stochastic label corruption process, we propose total variation regularization, which encourages the predicted probabilities to be more distinguishable from each other. Under mild assumptions, the proposed method yields a consistent estimator of the transition matrix. We show the effectiveness of the proposed method through experiments on benchmark and real-world datasets.

While semi-supervised learning (SSL) has received tremendous attentions in many machine learning tasks due to its successful use of unlabeled data, existing SSL algorithms use either all unlabeled examples or the unlabeled examples with a fixed high-confidence prediction during the training progress. However, it is possible that too many correct/wrong pseudo labeled examples are eliminated/selected. In this work we develop a simple yet powerful framework, whose key idea is to select a subset of training examples from the unlabeled data when performing existing SSL methods so that only the unlabeled examples with pseudo labels related to the labeled data will be used to train models. The selection is performed at each updating iteration by only keeping the examples whose losses are smaller than a given threshold that is dynamically adjusted through the iteration. Our proposed approach, Dash, enjoys its adaptivity in terms of unlabeled data selection and its theoretical guarantee. Specifically, we theoretically establish the convergence rate of Dash from the view of non-convex optimization. Finally, we empirically demonstrate the effectiveness of the proposed method in comparison with state-of-the-art over benchmarks.

Transformer based models, like BERT and RoBERTa, have achieved state-of-the-art results in many Natural Language Processing tasks. However, their memory footprint, inference latency, and power consumption are prohibitive efficient inference at the edge, and even at the data center. While quantization can be a viable solution for this, previous work on quantizing Transformer based models use floating-point arithmetic during inference, which cannot efficiently utilize integer-only logical units such as the recent Turing Tensor Cores, or traditional integer-only ARM processors. In this work, we propose I-BERT, a novel quantization scheme for Transformer based models that quantizes the entire inference with integer-only arithmetic. Based on lightweight integer-only approximation methods for nonlinear operations, e.g., GELU, Softmax, and Layer Normalization, I-BERT performs an end-to-end integer-only BERT inference without any floating point calculation. We evaluate our approach on GLUE downstream tasks using RoBERTa-Base/Large. We show that for both cases, I-BERT achieves similar (and slightly higher) accuracy as compared to the full-precision baseline. Furthermore, our preliminary implementation of I-BERT shows a speedup of 2.4- 4.0x for INT8 inference on a T4 GPU system as compared to FP32 inference. The framework has been developed in PyTorch and has been open-sourced.

In representation learning, there has been recent interest in developing algorithms to disentangle the ground-truth generative factors behind a dataset, and metrics to quantify how fully this occurs. However, these algorithms and metrics often assume that both representations and ground-truth factors are flat, continuous, and factorized, whereas many real-world generative processes involve rich hierarchical structure, mixtures of discrete and continuous variables with dependence between them, and even varying intrinsic dimensionality. In this work, we develop benchmarks, algorithms, and metrics for learning such hierarchical representations.

We propose, implement, and evaluate a new algo-rithm for releasing answers to very large numbersof statistical queries likek-way marginals, sub-ject to differential privacy. Our algorithm makesadaptive use of a continuous relaxation of thePro-jection Mechanism, which answers queries on theprivate dataset using simple perturbation, and thenattempts to find the synthetic dataset that mostclosely matches the noisy answers. We use a con-tinuous relaxation of the synthetic dataset domainwhich makes the projection loss differentiable,and allows us to use efficient ML optimizationtechniques and tooling. Rather than answering allqueries up front, we make judicious use of ourprivacy budget by iteratively finding queries forwhich our (relaxed) synthetic data has high error,and then repeating the projection. Randomizedrounding allows us to obtain synthetic data in theoriginal schema. We perform experimental evalu-ations across a range of parameters and datasets,and find that our method outperforms existingalgorithms on large query classes.

We introduce Deep Adaptive Design (DAD), a method for amortizing the cost of adaptive Bayesian experimental design that allows experiments to be run in real-time. Traditional sequential Bayesian optimal experimental design approaches require substantial computation at each stage of the experiment. This makes them unsuitable for most real-world applications, where decisions must typically be made quickly. DAD addresses this restriction by learning an amortized design network upfront and then using this to rapidly run (multiple) adaptive experiments at deployment time. This network represents a design policy which takes as input the data from previous steps, and outputs the next design using a single forward pass; these design decisions can be made in milliseconds during the live experiment. To train the network, we introduce contrastive information bounds that are suitable objectives for the sequential setting, and propose a customized network architecture that exploits key symmetries. We demonstrate that DAD successfully amortizes the process of experimental design, outperforming alternative strategies on a number of problems.

Randomized smoothing is a general technique for computing sample-dependent robustness guarantees against adversarial attacks for deep classifiers. Prior works on randomized smoothing against L*1 adversarial attacks use additive smoothing noise and provide probabilistic robustness guarantees. In this work, we propose a non-additive and deterministic smoothing method, Deterministic Smoothing with Splitting Noise (DSSN). To develop DSSN, we first develop SSN, a randomized method which involves generating each noisy smoothing sample by first randomly splitting the input space and then returning a representation of the center of the subdivision occupied by the input sample. In contrast to uniform additive smoothing, the SSN certification does not require the random noise components used to be independent. Thus, smoothing can be done effectively in just one dimension and can therefore be efficiently derandomized for quantized data (e.g., images). To the best of our knowledge, this is the first work to provide deterministic "randomized smoothing" for a norm-based adversarial threat model while allowing for an arbitrary classifier (i.e., a deep model) to be used as a base classifier and without requiring an exponential number of smoothing samples. On CIFAR-10 and ImageNet datasets, we provide substantially larger L*1 robustness certificates compared to prior works, establishing …

We provide an approximation algorithm for k-means clustering in the \emph{one-round} (aka \emph{non-interactive}) local model of differential privacy (DP). Our algorithm achieves an approximation ratio arbitrarily close to the best \emph{non private} approximation algorithm, improving upon previously known algorithms that only guarantee large (constant) approximation ratios. Furthermore, ours is the first constant-factor approximation algorithm for k-means that requires only \emph{one} round of communication in the local DP model, positively resolving an open question of Stemmer (SODA 2020). Our algorithmic framework is quite flexible; we demonstrate this by showing that it also yields a similar near-optimal approximation algorithm in the (one-round) shuffle DP model.

Self-supervised learning on graph-structured data has drawn recent interest for learning generalizable, transferable and robust representations from unlabeled graphs. Among many, graph contrastive learning (GraphCL) has emerged with promising representation learning performance. Unfortunately, unlike its counterpart on image data, the effectiveness of GraphCL hinges on ad-hoc data augmentations, which have to be manually picked per dataset, by either rules of thumb or trial-and-errors, owing to the diverse nature of graph data. That significantly limits the more general applicability of GraphCL. Aiming to fill in this crucial gap, this paper proposes a unified bi-level optimization framework to automatically, adaptively and dynamically select data augmentations when performing GraphCL on specific graph data. The general framework, dubbed JOint Augmentation Optimization (JOAO), is instantiated as min-max optimization. The selections of augmentations made by JOAO are shown to be in general aligned with previous "best practices" observed from handcrafted tuning: yet now being automated, more flexible and versatile. Moreover, we propose a new augmentation-aware projection head mechanism, which will route output features through different projection heads corresponding to different augmentations chosen at each training step. Extensive experiments demonstrate that JOAO performs on par with or sometimes better than the state-of-the-art competitors including GraphCL, on multiple …

Annealed Importance Sampling (AIS) and its Sequential Monte Carlo (SMC) extensions are state-of-the-art methods for estimating normalizing constants of probability distributions. We propose here a novel Monte Carlo algorithm, Annealed Flow Transport (AFT), that builds upon AIS and SMC and combines them with normalizing flows (NFs) for improved performance. This method transports a set of particles using not only importance sampling (IS), Markov chain Monte Carlo (MCMC) and resampling steps - as in SMC, but also relies on NFs which are learned sequentially to push particles towards the successive annealed targets. We provide limit theorems for the resulting Monte Carlo estimates of the normalizing constant and expectations with respect to the target distribution. Additionally, we show that a continuous-time scaling limit of the population version of AFT is given by a Feynman--Kac measure which simplifies to the law of a controlled diffusion for expressive NFs. We demonstrate experimentally the benefits and limitations of our methodology on a variety of applications.

Recursive Neural Networks (RvNNs), which compose sequences according to their underlying hierarchical syntactic structure, have performed well in several natural language processing tasks compared to similar models without structural biases. However, traditional RvNNs are incapable of inducing the latent structure in a plain text sequence on their own. Several extensions have been proposed to overcome this limitation. Nevertheless, these extensions tend to rely on surrogate gradients or reinforcement learning at the cost of higher bias or variance. In this work, we propose Continuous Recursive Neural Network (CRvNN) as a backpropagation-friendly alternative to address the aforementioned limitations. This is done by incorporating a continuous relaxation to the induced structure. We demonstrate that CRvNN achieves strong performance in challenging synthetic tasks such as logical inference (Bowman et al., 2015b) and ListOps (Nangia & Bowman, 2018). We also show that CRvNN performs comparably or better than prior latent structure models on real-world tasks such as sentiment analysis and natural language inference.

In the domain generalization literature, a common objective is to learn representations independent of the domain after conditioning on the class label. We show that this objective is not sufficient: there exist counter-examples where a model fails to generalize to unseen domains even after satisfying class-conditional domain invariance. We formalize this observation through a structural causal model and show the importance of modeling within-class variations for generalization. Specifically, classes contain objects that characterize specific causal features, and domains can be interpreted as interventions on these objects that change non-causal features. We highlight an alternative condition: inputs across domains should have the same representation if they are derived from the same object. Based on this objective, we propose matching-based algorithms when base objects are observed (e.g., through data augmentation) and approximate the objective when objects are not observed (MatchDG). Our simple matching-based algorithms are competitive to prior work on out-of-domain accuracy for rotated MNIST, Fashion-MNIST, PACS, and Chest-Xray datasets. Our method MatchDG also recovers ground-truth object matches: on MNIST and Fashion-MNIST, top-10 matches from MatchDG have over 50% overlap with ground-truth matches.

Performing reliable Bayesian inference on a big data scale is becoming a keystone in the modern era of machine learning. A workhorse class of methods to achieve this task are Markov chain Monte Carlo (MCMC) algorithms and their design to handle distributed datasets has been the subject of many works. However, existing methods are not completely either reliable or computationally efficient. In this paper, we propose to fill this gap in the case where the dataset is partitioned and stored on computing nodes within a cluster under a master/slaves architecture. We derive a user-friendly centralised distributed MCMC algorithm with provable scaling in high-dimensional settings. We illustrate the relevance of the proposed methodology on both synthetic and real data experiments.

We study the problem of differentially private (DP) matrix completion under user-level privacy. We design a joint differentially private variant of the popular Alternating-Least-Squares (ALS) method that achieves: i) (nearly) optimal sample complexity for matrix completion (in terms of number of items, users), and ii) the best known privacy/utility trade-off both theoretically, as well as on benchmark data sets. In particular, we provide the first global convergence analysis of ALS with noise introduced to ensure DP, and show that, in comparison to the best known alternative (the Private Frank-Wolfe algorithm by Jain et al. (2018)), our error bounds scale significantly better with respect to the number of items and users, which is critical in practical problems. Extensive validation on standard benchmarks demonstrate that the algorithm, in combination with carefully designed sampling procedures, is significantly more accurate than existing techniques, thus promising to be the first practical DP embedding model.

Transfer learning eases the burden of training a well-performed model from scratch, especially when training data is scarce and computation power is limited. In deep learning, a typical strategy for transfer learning is to freeze the early layers of a pre-trained model and fine-tune the rest of its layers on the target domain. Previous work focuses on the accuracy of the transferred model but neglects the transfer of adversarial robustness. In this work, we first show that transfer learning improves the accuracy on the target domain but degrades the inherited robustness of the target model. To address such a problem, we propose a novel cooperative adversarially-robust transfer learning (CARTL) by pre-training the model via feature distance minimization and fine-tuning the pre-trained model with non-expansive fine-tuning for target domain tasks. Empirical results show that CARTL improves the inherited robustness by about 28% at most compared with the baseline with the same degree of accuracy. Furthermore, we study the relationship between the batch normalization (BN) layers and the robustness in the context of transfer learning, and we reveal that freezing BN layers can further boost the robustness transfer.

The focus of disentanglement approaches has been on identifying independent factors of variation in data. However, the causal variables underlying real-world observations are often not statistically independent. In this work, we bridge the gap to real-world scenarios by analyzing the behavior of the most prominent disentanglement approaches on correlated data in a large-scale empirical study (including 4260 models). We show and quantify that systematically induced correlations in the dataset are being learned and reflected in the latent representations, which has implications for downstream applications of disentanglement such as fairness. We also demonstrate how to resolve these latent correlations, either using weak supervision during training or by post-hoc correcting a pre-trained model with a small number of labels.

Prosody plays an important role in characterizing the style of a speaker or an emotion, but most non-parallel voice or emotion style transfer algorithms do not convert any prosody information. Two major components of prosody are pitch and rhythm. Disentangling the prosody information, particularly the rhythm component, from the speech is challenging because it involves breaking the synchrony between the input speech and the disentangled speech representation. As a result, most existing prosody style transfer algorithms would need to rely on some form of text transcriptions to identify the content information, which confines their application to high-resource languages only. Recently, SpeechSplit has made sizeable progress towards unsupervised prosody style transfer, but it is unable to extract high-level global prosody style in an unsupervised manner. In this paper, we propose AutoPST, which can disentangle global prosody style from speech without relying on any text transcriptions. AutoPST is an Autoencoder-based Prosody Style Transfer framework with a thorough rhythm removal module guided by the self-expressive representation learning. Experiments on different style transfer tasks show that AutoPST can effectively convert prosody that correctly reflects the styles of the target domains.

We focus on prediction problems with structured outputs that are subject to output validity constraints, e.g. pseudocode-to-code translation where the code must compile. While labeled input-output pairs are expensive to obtain, "unlabeled" outputs, i.e. outputs without corresponding inputs, are freely available (e.g. code on GitHub) and provide information about output validity. Pre-training captures this structure by training a denoiser to denoise corrupted versions of unlabeled outputs. We first show that standard fine-tuning after pre-training destroys some of this structure. We then propose composed fine-tuning, which trains a predictor composed with the pre-trained denoiser. Importantly, the denoiser is fixed to preserve output structure. Like standard fine-tuning, the predictor is also initialized with the pre-trained denoiser. We prove for two-layer ReLU networks that composed fine-tuning significantly reduces the complexity of the predictor, thus improving generalization. Empirically, we show that composed fine-tuning improves over standard fine-tuning on two pseudocode-to-code translation datasets (3% and 6% relative). The improvement is magnified on out-of-distribution (OOD) examples (4% and 25% relative), suggesting that reducing predictor complexity improves OOD extrapolation.

We show that aggregated model updates in federated learning may be insecure. An untrusted central server may disaggregate user updates from sums of updates across participants given repeated observations, enabling the server to recover privileged information about individual users' private training data via traditional gradient inference attacks. Our method revolves around reconstructing participant information (e.g: which rounds of training users participated in) from aggregated model updates by leveraging summary information from device analytics commonly used to monitor, debug, and manage federated learning systems. Our attack is parallelizable and we successfully disaggregate user updates on settings with up to thousands of participants. We quantitatively and qualitatively demonstrate significant improvements in the capability of various inference attacks on the disaggregated updates. Our attack enables the attribution of learned properties to individual users, violating anonymity, and shows that a determined central server may undermine the secure aggregation protocol to break individual users' data privacy in federated learning.

Generating functions, which are widely used in combinatorics and probability theory, encode function values into the coefficients of a polynomial. In this paper, we explore their use as a tractable probabilistic model, and propose probabilistic generating circuits (PGCs) for their efficient representation. PGCs are strictly more expressive efficient than many existing tractable probabilistic models, including determinantal point processes (DPPs), probabilistic circuits (PCs) such as sum-product networks, and tractable graphical models. We contend that PGCs are not just a theoretical framework that unifies vastly different existing models, but also show great potential in modeling realistic data. We exhibit a simple class of PGCs that are not trivially subsumed by simple combinations of PCs and DPPs, and obtain competitive performance on a suite of density estimation benchmarks. We also highlight PGCs' connection to the theory of strongly Rayleigh distributions.

We view disentanglement learning as discovering an underlying structure that equivariantly reflects the factorized variations shown in data. Traditionally, such a structure is fixed to be a vector space with data variations represented by translations along individual latent dimensions. We argue this simple structure is suboptimal since it requires the model to learn to discard the properties (e.g. different scales of changes, different levels of abstractness) of data variations, which is an extra work than equivariance learning. Instead, we propose to encode the data variations with groups, a structure not only can equivariantly represent variations, but can also be adaptively optimized to preserve the properties of data variations. Considering it is hard to conduct training on group structures, we focus on Lie groups and adopt a parameterization using Lie algebra. Based on the parameterization, some disentanglement learning constraints are naturally derived. A simple model named Commutative Lie Group VAE is introduced to realize the group-based disentanglement learning. Experiments show that our model can effectively learn disentangled representations without supervision, and can achieve state-of-the-art performance without extra constraints.

Advanced large-scale neural language models have led to significant success in many language generation tasks. However, the most commonly used training objective, Maximum Likelihood Estimation (MLE), has been shown problematic, where the trained model prefers using dull and repetitive phrases. In this work, we introduce ScaleGrad, a modification straight to the gradient of the loss function, to remedy the degeneration issue of the standard MLE objective. By directly maneuvering the gradient information, ScaleGrad makes the model learn to use novel tokens. Empirical results show the effectiveness of our method not only in open-ended generation, but also in directed generation tasks. With the simplicity in architecture, our method can serve as a general training objective that is applicable to most of the neural text generation tasks.

The usual setting for learning the structure and parameters of a graphical model assumes the availability of independent samples produced from the corresponding multivariate probability distribution. However, for many models the mixing time of the respective Markov chain can be very large and i.i.d. samples may not be obtained. We study the problem of reconstructing binary graphical models from correlated samples produced by a dynamical process, which is natural in many applications. We analyze the sample complexity of two estimators that are based on the interaction screening objective and the conditional likelihood loss. We observe that for samples coming from a dynamical process far from equilibrium, the sample complexity reduces exponentially compared to a dynamical process that mixes quickly.

High-dimensional partial differential equations (PDEs) are ubiquitous in economics, science and engineering. However, their numerical treatment poses formidable challenges since traditional grid-based methods tend to be frustrated by the curse of dimensionality. In this paper, we argue that tensor trains provide an appealing approximation framework for parabolic PDEs: the combination of reformulations in terms of backward stochastic differential equations and regression-type methods in the tensor format holds the promise of leveraging latent low-rank structures enabling both compression and efficient computation. Following this paradigm, we develop novel iterative schemes, involving either explicit and fast or implicit and accurate updates. We demonstrate in a number of examples that our methods achieve a favorable trade-off between accuracy and computational efficiency in comparison with state-of-the-art neural network based approaches.

Task-specific fine-tuning on pre-trained transformers has achieved performance breakthroughs in multiple NLP tasks. Yet, as both computation and parameter size grows linearly with the number of sub-tasks, it is increasingly difficult to adopt such methods to the real world due to unrealistic memory and computation overhead on computing devices. Previous works on fine-tuning focus on reducing the growing parameter size to save storage cost by parameter sharing. However, compared to storage, the constraint of computation is a more critical issue with the fine-tuning models in modern computing environments. In this work, we propose LeTS, a framework that leverages both computation and parameter sharing across multiple tasks. Compared to traditional fine-tuning, LeTS proposes a novel neural architecture that contains a fixed pre-trained transformer model, plus learnable additive components for sub-tasks. The learnable components reuse the intermediate activations in the fixed pre-trained model, decoupling computation dependency. Differentiable neural architecture search is used to determine a task-specific computation sharing scheme, and a novel early stage pruning is applied to additive components for sparsity to achieve parameter sharing. Extensive experiments show that with 1.4% of extra parameters per task, LeTS reduces the computation by 49.5% on GLUE benchmarks with only 0.2% accuracy loss compared …

We present neural activation coding (NAC) as a novel approach for learning deep representations from unlabeled data for downstream applications. We argue that the deep encoder should maximize its nonlinear expressivity on the data for downstream predictors to take full advantage of its representation power. To this end, NAC maximizes the mutual information between activation patterns of the encoder and the data over a noisy communication channel. We show that learning for a noise-robust activation code increases the number of distinct linear regions of ReLU encoders, hence the maximum nonlinear expressivity. More interestingly, NAC learns both continuous and discrete representations of data, which we respectively evaluate on two downstream tasks: (i) linear classification on CIFAR-10 and ImageNet-1K and (ii) nearest neighbor retrieval on CIFAR-10 and FLICKR-25K. Empirical results show that NAC attains better or comparable performance on both tasks over recent baselines including SimCLR and DistillHash. In addition, NAC pretraining provides significant benefits to the training of deep generative models. Our code is available at https://github.com/yookoon/nac.

Distribution shifts---where the training distribution differs from the test distribution---can substantially degrade the accuracy of machine learning (ML) systems deployed in the wild. Despite their ubiquity in the real-world deployments, these distribution shifts are under-represented in the datasets widely used in the ML community today. To address this gap, we present WILDS, a curated benchmark of 10 datasets reflecting a diverse range of distribution shifts that naturally arise in real-world applications, such as shifts across hospitals for tumor identification; across camera traps for wildlife monitoring; and across time and location in satellite imaging and poverty mapping. On each dataset, we show that standard training yields substantially lower out-of-distribution than in-distribution performance. This gap remains even with models trained by existing methods for tackling distribution shifts, underscoring the need for new methods for training models that are more robust to the types of distribution shifts that arise in practice. To facilitate method development, we provide an open-source package that automates dataset loading, contains default model architectures and hyperparameters, and standardizes evaluations. The full paper, code, and leaderboards are available at https://wilds.stanford.edu.

The problem of finding an ancestral acyclic directed mixed graph (ADMG) that represents the causal relationships between a set of variables is an important area of research on causal inference. Most existing score-based structure learning methods focus on learning directed acyclic graph (DAG) models without latent variables. A number of score-based methods have recently been proposed for the ADMG learning, yet they are heuristic in nature and do not guarantee an optimal solution. We propose a novel exact score-based method that solves an integer programming (IP) formulation and returns a score-maximizing ancestral ADMG for a set of continuous variables that follow a multivariate Gaussian distribution. We generalize the state-of-the-art IP model for DAG learning problems and derive new classes of valid inequalities to formulate an IP model for ADMG learning. Empirically, our model can be solved efficiently for medium-sized problems and achieves better accuracy than state-of-the-art score-based methods as well as benchmark constraint-based methods.

Log-loss (also known as cross-entropy loss) metric is ubiquitously used across machine learning applications to assess the performance of classification algorithms. In this paper, we investigate the problem of inferring the labels of a dataset from single (or multiple) log-loss score(s), without any other access to the dataset. Surprisingly, we show that for any finite number of label classes, it is possible to accurately infer the labels of the dataset from the reported log-loss score of a single carefully constructed prediction vector if we allow arbitrary precision arithmetic. Additionally, we present label inference algorithms (attacks) that succeed even under addition of noise to the log-loss scores and under limited precision arithmetic. All our algorithms rely on ideas from number theory and combinatorics and require no model training. We run experimental simulations on some real datasets to demonstrate the ease of running these attacks in practice.

GPT-3 can perform numerous tasks when provided a natural language prompt that contains a few training examples. We show that this type of few-shot learning can be unstable: the choice of prompt format, training examples, and even the order of the examples can cause accuracy to vary from near chance to near state-of-the-art. We demonstrate that this instability arises from the bias of language models towards predicting certain answers, e.g., those that are placed near the end of the prompt or are common in the pre-training data. To mitigate this, we first estimate the model's bias towards each answer by asking for its prediction when given a training prompt and a content-free test input such as "N/A". We then fit calibration parameters that cause the prediction for this input to be uniform across answers. On a diverse set of tasks, this contextual calibration procedure substantially improves GPT-3 and GPT-2's accuracy (up to 30.0% absolute) across different choices of the prompt, while also making learning considerably more stable.

State-of-the-art computer vision systems are trained to predict a fixed set of predetermined object categories. This restricted form of supervision limits their generality and usability since additional labeled data is needed to specify any other visual concept. Learning directly from raw text about images is a promising alternative which leverages a much broader source of supervision. We demonstrate that the simple pre-training task of predicting which caption goes with which image is an efficient and scalable way to learn SOTA image representations from scratch on a dataset of 400 million (image, text) pairs collected from the internet. After pre-training, natural language is used to reference learned visual concepts (or describe new ones) enabling zero-shot transfer of the model to downstream tasks. We study the performance of this approach by benchmarking on over 30 different existing computer vision datasets, spanning tasks such as OCR, action recognition in videos, geo-localization, and many types of fine-grained object classification. The model transfers non-trivially to most tasks and is often competitive with a fully supervised baseline without the need for any dataset specific training. For instance, we match the accuracy of the original ResNet-50 on ImageNet zero-shot without needing to use any of the 1.28 …

Developing machine learning methods that are privacy preserving is today a central topic of research, with huge practical impacts. Among the numerous ways to address privacy-preserving learning, we here take the perspective of computing the divergences between distributions under the Differential Privacy (DP) framework --- being able to compute divergences between distributions is pivotal for many machine learning problems, such as learning generative models or domain adaptation problems. Instead of resorting to the popular gradient-based sanitization method for DP, we tackle the problem at its roots by focusing on the Sliced Wasserstein Distance and seamlessly making it differentially private. Our main contribution is as follows: we analyze the property of adding a Gaussian perturbation to the intrinsic randomized mechanism of the Sliced Wasserstein Distance, and we establish the sensitivity of the resulting differentially private mechanism. One of our important findings is that this DP mechanism transforms the Sliced Wasserstein distance into another distance, that we call the Smoothed Sliced Wasserstein Distance. This new differentially private distribution distance can be plugged into generative models and domain adaptation algorithms in a transparent way, and we empirically show that it yields highly competitive performance compared with gradient-based DP approaches from the literature, with …

We prove that the alpha-expansion algorithm for MAP inference always returns a globally optimal assignment for Markov Random Fields with Potts pairwise potentials, with a catch: the returned assignment is only guaranteed to be optimal for an instance within a small perturbation of the original problem instance. In other words, all local minima with respect to expansion moves are global minima to slightly perturbed versions of the problem. On "real-world" instances, MAP assignments of small perturbations of the problem should be very similar to the MAP assignment(s) of the original problem instance. We design an algorithm that can certify whether this is the case in practice. On several MAP inference problem instances from computer vision, this algorithm certifies that MAP solutions to all of these perturbations are very close to solutions of the original instance. These results taken together give a cohesive explanation for the good performance of "graph cuts" algorithms in practice. Every local expansion minimum is a global minimum in a small perturbation of the problem, and all of these global minima are close to the original solution.

Detecting anomalous inputs, such as adversarial and out-of-distribution (OOD) inputs, is critical for classifiers (including deep neural networks or DNNs) deployed in real-world applications. While prior works have proposed various methods to detect such anomalous samples using information from the internal layer representations of a DNN, there is a lack of consensus on a principled approach for the different components of such a detection method. As a result, often heuristic and one-off methods are applied for different aspects of this problem. We propose an unsupervised anomaly detection framework based on the internal DNN layer representations in the form of a meta-algorithm with configurable components. We proceed to propose specific instantiations for each component of the meta-algorithm based on ideas grounded in statistical testing and anomaly detection. We evaluate the proposed methods on well-known image classification datasets with strong adversarial attacks and OOD inputs, including an adaptive attack that uses the internal layer representations of the DNN (often not considered in prior work). Comparisons with five recently-proposed competing detection methods demonstrates the effectiveness of our method in detecting adversarial and OOD inputs.

Correlation clustering is a central topic in unsupervised learning, with many applications in ML and data mining. In correlation clustering, one receives as input a signed graph and the goal is to partition it to minimize the number of disagreements. In this work we propose a massively parallel computation (MPC) algorithm for this problem that is considerably faster than prior work. In particular, our algorithm uses machines with memory sublinear in the number of nodes in the graph and returns a constant approximation while running only for a constant number of rounds. To the best of our knowledge, our algorithm is the first that can provably approximate a clustering problem using only a constant number of MPC rounds in the sublinear memory regime. We complement our analysis with an experimental scalability evaluation of our techniques.

We propose a new training objective named order-agnostic cross entropy (OaXE) for fully non-autoregressive translation (NAT) models. OaXE improves the standard cross-entropy loss to ameliorate the effect of word reordering, which is a common source of the critical multimodality problem in NAT. Concretely, OaXE removes the penalty for word order errors, and computes the cross entropy loss based on the best possible alignment between model predictions and target tokens. Since the log loss is very sensitive to invalid references, we leverage cross entropy initialization and loss truncation to ensure the model focuses on a good part of the search space. Extensive experiments on major WMT benchmarks demonstrate that OaXE substantially improves translation performance, setting new state of the art for fully NAT models. Further analyses show that OaXE indeed alleviates the multimodality problem by reducing token repetitions and increasing prediction confidence. Our code, data, and trained models are available at https://github.com/tencent-ailab/ICML21_OAXE.

Despite the recent success of graph neural networks (GNN), common architectures often exhibit significant limitations, including sensitivity to oversmoothing, long-range dependencies, and spurious edges, e.g., as can occur as a result of graph heterophily or adversarial attacks. To at least partially address these issues within a simple transparent framework, we consider a new family of GNN layers designed to mimic and integrate the update rules of two classical iterative algorithms, namely, proximal gradient descent and iterative reweighted least squares (IRLS). The former defines an extensible base GNN architecture that is immune to oversmoothing while nonetheless capturing long-range dependencies by allowing arbitrary propagation steps. In contrast, the latter produces a novel attention mechanism that is explicitly anchored to an underlying end-to-end energy function, contributing stability with respect to edge uncertainty. When combined we obtain an extremely simple yet robust model that we evaluate across disparate scenarios including standardized benchmarks, adversarially-perturbated graphs, graphs with heterophily, and graphs involving long-range dependencies. In doing so, we compare against SOTA GNN approaches that have been explicitly designed for the respective task, achieving competitive or superior node classification accuracy. Our code is available at https://github.com/FFTYYY/TWIRLS. And for an extended version of this work, please see https://arxiv.org/abs/2103.06064.

Unsupervised learning of the Dawid-Skene (D&S) model from noisy, incomplete and crowdsourced annotations has been a long-standing challenge, and is a critical step towards reliably labeling massive data. A recent work takes a coupled nonnegative matrix factorization (CNMF) perspective, and shows appealing features: It ensures the identifiability of the D\&S model and enjoys low sample complexity, as only the estimates of the co-occurrences of annotator labels are involved. However, the identifiability holds only when certain somewhat restrictive conditions are met in the context of crowdsourcing. Optimizing the CNMF criterion is also costly---and convergence assurances are elusive. This work recasts the pairwise co-occurrence based D&S model learning problem as a symmetric NMF (SymNMF) problem---which offers enhanced identifiability relative to CNMF. In practice, the SymNMF model is often (largely) incomplete, due to the lack of co-labeled items by some annotators. Two lightweight algorithms are proposed for co-occurrence imputation. Then, a low-complexity shifted rectified linear unit (ReLU)-empowered SymNMF algorithm is proposed to identify the D&S model. Various performance characterizations (e.g., missing co-occurrence recoverability, stability, and convergence) and evaluations are also presented.

State-of-the-art methods for scalable Gaussian processes use iterative algorithms, requiring fast matrix vector multiplies (MVMs) with the co-variance kernel. The Structured Kernel Interpolation (SKI) framework accelerates these MVMs by performing efficient MVMs on a grid and interpolating back to the original space. In this work, we develop a connection between SKI and the permutohedral lattice used for high-dimensional fast bilateral filtering. Using a sparse simplicial grid instead of a dense rectangular one, we can perform GP inference exponentially faster in the dimension than SKI. Our approach, Simplex-GP, enables scaling SKI to high dimensions, while maintaining strong predictive performance. We additionally provide a CUDA implementation of Simplex-GP, which enables significant GPU acceleration of MVM based inference.

In neural machine translation, Cross Entropy loss (CE) is the standard loss function in two training methods of auto-regressive models, i.e., teacher forcing and scheduled sampling. In this paper, we propose mixed Cross Entropy loss (mixed CE) as a substitute for CE in both training approaches. In teacher forcing, the model trained with CE regards the translation problem as a one-to-one mapping process, while in mixed CE this process can be relaxed to one-to-many. In scheduled sampling, we show that mixed CE has the potential to encourage the training and testing behaviours to be similar to each other, more effectively mitigating the exposure bias problem. We demonstrate the superiority of mixed CE over CE on several machine translation datasets, WMT'16 Ro-En, WMT'16 Ru-En, and WMT'14 En-De in both teacher forcing and scheduled sampling setups. Furthermore, in WMT'14 En-De, we also find mixed CE consistently outperforms CE on a multi-reference set as well as a challenging paraphrased reference set. We also found the model trained with mixed CE is able to provide a better probability distribution defined over the translation output space. Our code is available at https://github.com/haorannlp/mix.