ICML 2018

Search Schedule »

Search:

Session:

Event type:

Hide breaks and receptions:

Day:

Show All »

Timezone: Europe/Stockholm »

Indicates the beginning of a session

Time	Victoria	A9	A1	Hall B	K1 + K2
Tue Jul 10, 2018
09:15 AM (Tutorials)	Imitation Learning	Machine Learning in Automated Mechanism Design for Pricing and Auctions			Learning with Temporal Point Processes
01:00 PM (Tutorials)	Toward Theoretical Understanding of Deep Learning	Understanding your Neighbors: Practical Perspectives From Modern Analysis			Defining and Designing Fair Algorithms
03:45 PM (Tutorials)	Variational Bayes and Beyond: Bayesian Inference for Big Data	Optimization Perspectives on Learning to Control			Machine Learning for Personalised Health
03:00 AM (Breaks)				Opening Reception
08:45 AM (Talks)			Opening Remarks

Time	Victoria	A9	A3	A1	Hall B	A4	A7	K11	A5	K1 + K2	A6
Wed Jul 11, 2018
09:00 AM (Invited Talks)				AI and Security: Lessons, Challenges and Future Directions
11:00 AM (Orals)	Deep Learning (Neural Network Architectures) 1 DiCE: The Infinitely Differentiable Monte Carlo Estimator	Parallel and Distributed Learning 1 Optimal Tuning for Divide-and-conquer Kernel Ridge Regression with Massive Data	Transfer and Multi-Task Learning 1 Transfer Learning via Learning to Transfer	Reinforcement Learning 1 Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs		Unsupervised Learning 1 Crowdsourcing with Arbitrary Adversaries	Representation Learning 1 Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry	Clustering 1 Equivalence of Multicategory SVM and Simplex Cone SVM: Fast Computations and Statistical Theory	Structured Prediction 1 Predict and Constrain: Modeling Cardinality in Deep Structured Prediction	Feature Selection 1 Learning to Explain: An Information-Theoretic Perspective on Model Interpretation	Statistical Learning Theory 1 Nonparametric Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information
11:20 AM (Orals)	Learning to search with MCTSnets	Distributed Nonparametric Regression under Communication Constraints	Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory	Learning with Abandonment		Analysis of Minimax Error Rate for Crowdsourcing and Its Application to Worker Clustering Model	Hyperbolic Entailment Cones for Learning Hierarchical Embeddings	Quickshift++: Provably Good Initializations for Sample-Based Mean Shift	SparseMAP: Differentiable Sparse Structured Inference	Nonoverlap-Promoting Variable Selection	Do Outliers Ruin Collaboration?
11:30 AM (Orals)	Differentiable plasticity: training plastic neural networks with backpropagation	Coded Sparse Matrix Multiplication		Lipschitz Continuity in Model-based Reinforcement Learning		Conditional Noise-Contrastive Estimation of Unnormalised Models	Tree Edit Distance Learning via Adaptive Symbol Embeddings	Hierarchical Clustering with Structural Constraints		MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning	LeapsAndBounds: A Method for Approximately Optimal Algorithm Configuration
11:40 AM (Orals)	TACO: Learning Task Decomposition via Temporal Alignment for Control	Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication	Bilevel Programming for Hyperparameter Optimization and Meta-Learning	Implicit Quantile Networks for Distributional Reinforcement Learning		Deep One-Class Classification	Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations	K-means clustering using random matrix sparsification	Efficient and Consistent Adversarial Bipartite Matching	Black Box FDR	Variational Network Inference: Strong and Stable with Concrete Support
11:50 AM (Orals)	Graph Networks as Learnable Physics Engines for Inference and Control	Faster Derivative-Free Stochastic Algorithm for Shared Memory Machines	Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing—and Back	More Robust Doubly Robust Off-policy Evaluation		Deep Density Destructors	CoVeR: Learning Covariate-Specific Vector Representations with Tensor Decompositions	Clustering Semi-Random Mixtures of Gaussians	Learning to Speed Up Structured Output Prediction	Variable Selection via Penalized Neural Network: a Drop-Out-One Loss Approach	Network Global Testing by Counting Graphlets
01:30 PM (Orals)	Deep Learning (Neural Network Architectures) 2 RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks	Optimization (Non-convex) 1 Asynchronous Decentralized Parallel Stochastic Gradient Descent	Optimization (Bayesian) 1 Stagewise Safe Bayesian Optimization with Gaussian Processes	Reinforcement Learning 2 Coordinated Exploration in Concurrent Reinforcement Learning		Gaussian Processes 1 Markov Modulated Gaussian Cox Processes for Semi-Stationary Intensity Modeling of Events Data	Representation Learning 2 Improving Optimization in Models With Continuous Symmetry Breaking	Dimensionality Reduction 1 Leveraging Well-Conditioned Bases: Streaming and Distributed Summaries in Minkowski $p$-Norms	Sparsity and Compressed Sensing 1 WHInter: A Working set algorithm for High-dimensional sparse second order Interaction models	Other Applications 1 Limits of Estimating Heterogeneous Treatment Effects: Guidelines for Practical Algorithm Design	Statistical Learning Theory 2 Data-Dependent Stability of Stochastic Gradient Descent
01:50 PM (Orals)	Semi-Supervised Learning via Compact Latent Space Clustering	signSGD: Compressed Optimisation for Non-Convex Problems	BOCK : Bayesian Optimization with Cylindrical Kernels	Structured Evolution with Compact Architectures for Scalable Policy Optimization		Bayesian Quadrature for Multiple Related Integrals	A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks	Subspace Embedding and Linear Regression with Orlicz Norm	Nearly Optimal Robust Subspace Tracking	Variance Regularized Counterfactual Risk Minimization via Variational Divergence Minimization	Stability and Generalization of Learning Algorithms that Converge to Global Optima
02:00 PM (Orals)				Spotlight: Optimizing Device Placement for Training Deep Neural Networks
02:10 PM (Orals)	Conditional Neural Processes	Katyusha X: Simple Momentum Method for Stochastic Sum-of-Nonconvex Optimization	BOHB: Robust and Efficient Hyperparameter Optimization at Scale	Gated Path Planning Networks		Differentiable Compositional Kernel Learning for Gaussian Processes	Learning Steady-States of Iterative Algorithms over Graphs	Stochastic PCA with $\ell_2$ and $\ell_1$ Regularization	Safe Element Screening for Submodular Function Minimization	An Estimation and Analysis Framework for the Rasch Model	Optimal Rates of Sketched-regularized Algorithms for Least-Squares Regression over Hilbert Spaces
02:20 PM (Orals)	A Semantic Loss Function for Deep Learning with Symbolic Knowledge	$D^2$: Decentralized Training over Decentralized Data	Bayesian Optimization of Combinatorial Structures	Best Arm Identification in Linear Bandits with Linear Dimension Dependency		Generalized Robust Bayesian Committee Machine for Large-scale Gaussian Process Regression	Anonymous Walk Embeddings	Streaming Principal Component Analysis in Noisy Setting	Online Convolutional Sparse Coding with Sample-Dependent Dictionary	End-to-end Active Object Tracking via Reinforcement Learning	Dropout Training, Data-dependent Regularization, and Generalization Bounds
02:30 PM (Orals)	Deep Learning (Neural Network Architectures) 3 Non-linear motor control by local learning in spiking neural networks	Optimization (Non-convex) 2 An Alternative View: When Does SGD Escape Local Minima?	Active Learning 1 Design of Experiments for Model Discrimination Hybridising Analytical and Data-Driven Approaches	Reinforcement Learning 3 Structured Control Nets for Deep Reinforcement Learning		Deep Learning (Bayesian) 1 Variational Inference and Model Selection with Generalized Evidence Bounds	Representation Learning 3 Generative Temporal Models with Spatial Memory for Partially Observed Environments	Sparsity and Compressed Sensing 2 Linear Spectral Estimators and an Application to Phase Retrieval	Ranking and Preference Learning 1 The Limits of Maxing, Ranking, and Preference Learning	Computer Vision 1 Deep Predictive Coding Network for Object Recognition	Statistical Learning Theory 3 Information Theoretic Guarantees for Empirical Risk Minimization with Applications to Model Selection and Large-Scale Optimization
02:50 PM (Orals)	PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning	Escaping Saddles with Stochastic Gradients	Selecting Representative Examples for Program Synthesis	Latent Space Policies for Hierarchical Reinforcement Learning		Fixing a Broken ELBO	Disentangling by Factorising	Covariate Adjusted Precision Matrix Estimation via Nonconvex Optimization	Learning a Mixture of Two Multinomial Logits	Gradually Updated Neural Networks for Large-Scale Image Recognition	The Generalization Error of Dictionary Learning with Moreau Envelopes
03:00 PM (Orals)	Hierarchical Long-term Video Prediction without Supervision						Discovering Interpretable Representations for Both Deep Generative and Discriminative Models		The Weighted Kendall and High-order Kernels for Permutations	Neural Inverse Rendering for General Reflectance Photometric Stereo	On Learning Sparsely Used Dictionaries from Incomplete Samples
03:10 PM (Orals)	Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search	Stochastic Variance-Reduced Cubic Regularized Newton Method	On the Relationship between Data Efficiency and Error for Uncertainty Sampling	Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings		Tighter Variational Bounds are Not Necessarily Better	Learning Independent Causal Mechanisms	Signal and Noise Statistics Oblivious Orthogonal Matching Pursuit	Parameterized Algorithms for the Matrix Completion Problem	One-Shot Segmentation in Clutter	The Well-Tempered Lasso
03:20 PM (Orals)	Model-Level Dual Learning	Non-convex Conditional Gradient Sliding		An Inference-Based Policy Gradient Method for Learning Options		Continuous-Time Flows for Efficient Inference and Density Estimation	Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing	Testing Sparsity over Known and Unknown Bases		Active Testing: An Efficient and Robust Framework for Estimating Accuracy	Differentially Private Identity and Equivalence Testing of Discrete Distributions
04:00 PM (Orals)	Deep Learning (Neural Network Architectures) 4 Adafactor: Adaptive Learning Rates with Sublinear Memory Cost	Optimization (Convex) 1 Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs	Reinforcement Learning 5 Competitive Multi-agent Inverse Reinforcement Learning with Sub-optimal Demonstrations	Reinforcement Learning 4 Programmatically Interpretable Reinforcement Learning		Approximate Inference 1 Semi-Implicit Variational Inference	Generative Models 1 Which Training Methods for GANs do actually Converge?	Optimization (Combinatorial) 1 Weakly Submodular Maximization Beyond Cardinality Constraints: Does Randomization Help Greedy?	Networks and Relational Learning 1 Stochastic Training of Graph Convolutional Networks with Variance Reduction	Deep Learning (Theory) 1 Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks	Privacy, Anonymity, and Security 1 Differentially Private Matrix Completion Revisited
04:20 PM (Orals)	Orthogonal Recurrent Neural Networks with Scaled Cayley Transform	Lyapunov Functions for First-Order Methods: Tight Automated Convergence Guarantees	Feedback-Based Tree Search for Reinforcement Learning	Learning by Playing - Solving Sparse Reward Tasks from Scratch		Efficient Gradient-Free Variational Inference using Policy Search	Chi-square Generative Adversarial Network	Beyond 1/2-Approximation for Submodular Maximization on Massive Data Streams	Representation Learning on Graphs with Jumping Knowledge Networks	The Dynamics of Learning: A Random Matrix Approach	Mitigating Bias in Adaptive Data Gathering via Differential Privacy
04:30 PM (Orals)	Kronecker Recurrent Units	ADMM and Accelerated ADMM as Continuous Dynamical Systems									Local Private Hypothesis Testing: Chi-Square Tests
04:40 PM (Orals)	Fast Parametric Learning with Activation Memorization	Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn's Algorithm	Deep Reinforcement Learning in Continuous Action Spaces: a Case Study in the Game of Simulated Curling	Automatic Goal Generation for Reinforcement Learning Agents		A Spectral Approach to Gradient Estimation for Implicit Distributions	Learning Implicit Generative Models with the Method of Learned Moments	Scalable Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints	Learning Diffusion using Hyperparameters	On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization	Locally Private Hypothesis Testing
04:50 PM (Orals)	Dynamic Evaluation of Neural Sequence Models	An Efficient Semismooth Newton based Algorithm for Convex Clustering	Learning the Reward Function for a Misspecified Model	Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control		Quasi-Monte Carlo Variational Inference	A Classification-Based Study of Covariate Shift in GAN Distributions	Data Summarization at Scale: A Two-Stage Submodular Approach	Canonical Tensor Decomposition for Knowledge Base Completion	Deep Linear Networks with Arbitrary Loss: All Local Minima Are Global	INSPECTRE: Privately Estimating the Unseen
05:00 PM (Orals)	Deep Learning (Neural Network Architectures) 5 Decoupled Parallel Backpropagation with Convergence Guarantee	Optimization (Convex) 2 The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning	Reinforcement Learning 7 Machine Theory of Mind	Reinforcement Learning 6 Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning		Approximate Inference 2 Yes, but Did It Work?: Evaluating Variational Inference	Deep Learning (Adversarial) 1 Differentiable Abstract Interpretation for Provably Robust Neural Networks	Optimization (Combinatorial) 2 Learning to Optimize Combinatorial Functions	Networks and Relational Learning 2 Dependent Relational Gamma Process Models for Longitudinal Networks	Deep Learning (Theory) 2 Essentially No Barriers in Neural Network Energy Landscape	Society Impacts of Machine Learning 1 Delayed Impact of Fair Machine Learning
05:20 PM (Orals)	Efficient Neural Architecture Search via Parameters Sharing	Fast Variance Reduction Method with Stochastic Batch Size	Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement	Path Consistency Learning in Tsallis Entropy Regularized MDPs		Augment and Reduce: Stochastic Inference for Large Categorical Distributions	Provable Defenses against Adversarial Examples via the Convex Outer Adversarial Polytope	Proportional Allocation: Simple, Distributed, and Diverse Matching with High Entropy	NetGAN: Generating Graphs via Random Walks	Comparing Dynamics: Deep Neural Networks versus Glassy Systems	Fairness Without Demographics in Repeated Loss Minimization
05:30 PM (Orals)		SGD and Hogwild! Convergence Without the Bounded Gradients Assumption						Binary Partitions with Approximate Minimum Impurity		Not All Samples Are Created Equal: Deep Learning with Importance Sampling
05:40 PM (Orals)	Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization	Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data	Been There, Done That: Meta-Learning with Episodic Recall	Improved Regret Bounds for Thompson Sampling in Linear Quadratic Control Problems		Black-Box Variational Inference for Stochastic Differential Equations	Synthesizing Robust Adversarial Examples	Partial Optimality and Fast Lower Bounds for Weighted Correlation Clustering	GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models	Learning Deep ResNet Blocks Sequentially using Boosting Theory	Nonconvex Optimization for Regression with Fairness Constraints
05:50 PM (Orals)	Spline Filters For End-to-End Deep Learning	A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates	Continual Reinforcement Learning with Complex Synapses	Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator		Inference Suboptimality in Variational Autoencoders	Adversarial Risk and the Dangers of Evaluating Against Weak Attacks	Bounds on the Approximation Power of Feedforward Neural Networks	Neural Relational Inference for Interacting Systems	An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks	Fair and Diverse DPP-Based Data Summarization
06:15 PM (Posters)					Posters Wed
03:15 AM (Breaks)					Light Evening Snack

Time	B2	K12	Victoria	A9	A3	A1	Hall B	A4	A7	K1	K11	A5	A6	K2	T3	B9	B3	B5	K24	K23	K16	T4	K22
Thu Jul 12, 2018
09:00 AM (Invited Talks)						Intelligence per Kilowatthour
11:00 AM (Orals)			Deep Learning (Neural Network Architectures) 6 Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care	Parallel and Distributed Learning 2 Exploring Hidden Dimensions in Accelerating Convolutional Neural Networks	Multi-Agent Learning 1 Learning Policy Representations in Multiagent Systems	Reinforcement Learning 8 Convergent Tree Backup and Retrace with Function Approximation		Gaussian Processes 2 Learning unknown ODE models with Gaussian processes	Generative Models 2 Geometry Score: A Method For Comparing Generative Adversarial Networks	Other Applications 2 Learning Memory Access Patterns	Matrix Factorization 1 Probabilistic Boolean Tensor Decomposition	Structured Prediction 2 Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time	Privacy, Anonymity, and Security 2 Multicalibration: Calibration for the (Computationally-Identifiable) Masses
11:20 AM (Orals)			Compressing Neural Networks using the Variational Information Bottelneck	Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization	Learning to Coordinate with Coordination Graphs in Repeated Single-Stage Multi-Agent Decision Problems	SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation		Constraining the Dynamics of Deep Probabilistic Models	Optimizing the Latent Space of Generative Networks	Geodesic Convolutional Shape Optimization	A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery	Differentiable Dynamic Programming for Structured Prediction and Attention	Residual Unfairness in Fair Machine Learning from Prejudiced Data
11:30 AM (Orals)					Learning to Act in Decentralized Partially Observable MDPs				Adversarial Learning with Local Coordinate Coding		Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval and Matrix Completion		Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising
11:40 AM (Orals)			Kernelized Synaptic Weight Matrices	DICOD: Distributed Convolutional Coordinate Descent for Convolutional Sparse Coding	Modeling Others using Oneself in Multi-Agent Reinforcement Learning	Scalable Bilinear Pi Learning Using State and Action Features		Probabilistic Recurrent State-Space Models	Learning Representations and Generative Models for 3D Point Clouds	AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning	Learning Binary Latent Variable Models: A Tensor Eigenpair Approach	Structured Output Learning with Abstention: Application to Accurate Opinion Prediction	Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms
11:50 AM (Orals)			Deep Models of Interactions Across Sets	Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go?	QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning	Stochastic Variance-Reduced Policy Gradient		Structured Variationally Auto-encoded Optimization	Theoretical Analysis of Image-to-Image Translation with Adversarial Learning	TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service	Closed-form Marginal Likelihood in Gamma-Poisson Matrix Factorization	End-to-End Learning for the Deep Multivariate Probit Model	Adversarial Regression with Multiple Learners
01:30 PM (Orals)			Deep Learning (Neural Network Architectures) 7 Focused Hierarchical RNNs for Conditional Sequence Processing	Optimization (Convex) 3 Shampoo: Preconditioned Stochastic Tensor Optimization	Optimization (Bayesian) 2 Fast Information-theoretic Bayesian Optimisation	Reinforcement Learning 9 Investigating Human Priors for Playing Video Games		Monte Carlo Methods 1 Error Estimation for Randomized Least-Squares Algorithms via the Bootstrap	Deep Learning (Adversarial) 2 Composite Functional Gradient Learning of Generative Adversarial Models	Deep Learning (Theory) 3 Learning One Convolutional Layer with Overlapping Patches	Large Scale Learning and Big Data 1 Improved large-scale graph learning through ridge spectral sparsification	Ranking and Preference Learning 2 Accelerated Spectral Ranking	Supervised Learning 1 Inductive Two-Layer Modeling with Parametric Bregman Transfer
01:50 PM (Orals)			Learn from Your Neighbor: Learning Multi-modal Mappings from Sparse Annotations	Characterizing Implicit Bias in Terms of Optimization Geometry	Optimization, fast and slow: optimally switching between local and Bayesian optimization	Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?		Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization	Tempered Adversarial Networks	Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima	Parallel and Streaming Algorithms for K-Core Decomposition	Composite Marginal Likelihood Methods for Random Utility Models	Does Distributionally Robust Supervised Learning Give Robust Classifiers?
02:00 PM (Orals)				A Distributed Second-Order Algorithm You Can Trust		GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms		Stochastic Variance-Reduced Hamilton Monte Carlo Methods	Improved Training of Generative Adversarial Networks Using Representative Features			Ranking Distributions based on Noisy Sorting	Prediction Rule Reshaping
02:10 PM (Orals)			Learning long term dependencies via Fourier recurrent units	A Delay-tolerant Proximal-Gradient Algorithm for Distributed Learning	Batch Bayesian Optimization via Multi-objective Acquisition Ensemble for Automated Analog Circuit Design	Time Limits in Reinforcement Learning		A Robust Approach to Sequential Information Theoretic Planning	A Two-Step Computation of the Exact GAN Wasserstein Distance	The Multilinear Structure of ReLU Networks	Fast Approximate Spectral Clustering for Dynamic Networks	SQL-Rank: A Listwise Approach to Collaborative Ranking	Finding Influential Training Samples for Gradient Boosted Decision Trees
02:20 PM (Orals)			Training Neural Machines with Trace-Based Supervision	Gradient Coding from Cyclic MDS Codes and Expander Graphs	Tight Regret Bounds for Bayesian Optimization in One Dimension	Visualizing and Understanding Atari Agents		Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms	Is Generator Conditioning Causally Related to GAN Performance?	Understanding the Loss Surface of Neural Networks for Binary Classification	Matrix Norms in Data Streams: Faster, Multi-Pass and Row-Order	Extreme Learning to Rank via Low Rank Assumption	Noise2Noise: Learning Image Restoration without Clean Data
02:30 PM (Orals)			Deep Learning (Neural Network Architectures) 8 Neural Dynamic Programming for Musical Self Similarity	Optimization (Convex) 4 Alternating Randomized Block Coordinate Descent	Kernel Methods 1 To Understand Deep Learning We Need to Understand Kernel Learning	Reinforcement Learning 10 The Mirage of Action-Dependent Baselines in Reinforcement Learning		Graphical Models 1 Robust and Scalable Models of Microbiome Dynamics	Deep Learning (Adversarial) 3 Black-box Adversarial Attacks with Limited Queries and Information	Deep Learning (Theory) 4 Tropical Geometry of Deep Neural Networks	Large Scale Learning and Big Data 2 Near Optimal Frequent Directions for Sketching Dense and Sparse Matrices	Online Learning 1 Feasible Arm Identification	Supervised Learning 2 Dimensionality-Driven Learning with Noisy Labels
02:50 PM (Orals)			A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music	Randomized Block Cubic Newton Method	Kernel Recursive ABC: Point Estimation with Intractable Likelihood	Smoothed Action Value Functions for Learning Gaussian Policies		Stein Variational Message Passing for Continuous Graphical Models	Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples	A Spline Theory of Deep Learning	Loss Decomposition for Fast Learning in Large Output Spaces	Bandits with Delayed, Aggregated Anonymous Feedback	MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels
03:00 PM (Orals)			Fast Decoding in Sequence Models Using Discrete Latent Variables					A Fast and Scalable Joint Estimator for Integrating Additional Knowledge in Learning Multiple Related Sparse Gaussian Graphical Models			Ultra Large-Scale Feature Selection using Count-Sketches		Learning to Reweight Examples for Robust Deep Learning
03:10 PM (Orals)			PixelSNAIL: An Improved Autoregressive Generative Model	Accelerating Greedy Coordinate Descent Methods	Differentially Private Database Release via Kernel Mean Embeddings	Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor		Large-Scale Sparse Inverse Covariance Estimation via Thresholding and Max-Det Matrix Completion	Adversarial Attack on Graph Structured Data	Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions	Approximate Leave-One-Out for Fast Parameter Tuning in High Dimensions	Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits	Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks
03:20 PM (Orals)			Image Transformer	On Acceleration with Noise-Corrupted Gradients	Learning in Reproducing Kernel Kreı̆n Spaces	Addressing Function Approximation Error in Actor-Critic Methods		Bucket Renormalization for Approximate Inference	GAIN: Missing Data Imputation using Generative Adversarial Nets	Stronger Generalization Bounds for Deep Nets via a Compression Approach	Semi-Supervised Learning on Data Streams via Temporal Label Propagation	Thompson Sampling for Combinatorial Semi-Bandits	Improving Regression Performance with Distributional Losses
04:00 PM (Orals)			Deep Learning (Neural Network Architectures) 9 Using Inherent Structures to design Lean 2-layer RBMs	Optimization (Non-convex) 3 Approximate message passing for amplitude based optimization	Natural Language and Speech Processing 1 Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron	Reinforcement Learning 11 Configurable Markov Decision Processes		Deep Learning (Bayesian) 2 Variational Bayesian dropout: pitfalls and fixes	Deep Learning (Adversarial) 4 The Mechanics of n-Player Differentiable Games	Deep Learning (Theory) 5 Reviving and Improving Recurrent Back-Propagation	Optimization (Combinatorial) 3 Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings	Online Learning 2 Projection-Free Online Optimization with Stochastic Gradient: From Convexity to Submodularity	Statistical Learning Theory 4 Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods
04:20 PM (Orals)			Deep Asymmetric Multi-task Feature Learning	Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients	Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis	Beyond the One-Step Greedy Approach in Reinforcement Learning		Accurate Uncertainties for Deep Learning Using Calibrated Regression	K-Beam Minimax: Efficient Optimization for Deep Adversarial Learning	Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks	Approximation Guarantees for Adaptive Sampling	Practical Contextual Bandits with Regression Oracles	Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
04:30 PM (Orals)			Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations					Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning	First Order Generative Adversarial Networks	Invariance of Weight Distributions in Rectified MLPs	Greed is Still Good: Maximizing Monotone Submodular+Supermodular (BP) Functions
04:40 PM (Orals)			Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples	prDeep: Robust Phase Retrieval with a Flexible Deep Network	Fitting New Speakers Based on a Short Untranscribed Sample	Policy and Value Transfer in Lifelong Reinforcement Learning		Scalable approximate Bayesian inference for particle tracking data	Towards Fast Computation of Certified Robustness for ReLU Networks	Learning Dynamics of Linear Denoising Autoencoders	Constrained Interacting Submodular Groupings	Fast Stochastic AUC Maximization with $O(1/n)$-Convergence Rate	Functional Gradient Boosting based on Residual Network Perception
04:50 PM (Orals)			High Performance Zero-Memory Overhead Direct Convolutions	Accelerating Natural Gradient with Higher-Order Invariance	Towards Binary-Valued Gates for Robust LSTM Training	Importance Weighted Transfer of Samples in Reinforcement Learning		Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam	LaVAN: Localized and Visible Adversarial Noise	Understanding Generalization and Optimization Performance of Deep CNNs	Fast Maximization of Non-Submodular, Monotonic Functions on the Integer Lattice	Stochastic Proximal Algorithms for AUC Maximization	Binary Classification with Karmic, Threshold-Quasi-Concave Metrics
05:00 PM (Orals)			Deep Learning (Neural Network Architectures) 10 ContextNet: Deep learning for Star Galaxy Classification	Optimization (Non-convex) 4 Stochastic Wasserstein Barycenters	Reinforcement Learning 13 Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation	Reinforcement Learning 12 An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning		Deep Learning (Bayesian) 3 Neural Autoregressive Flows	Deep Learning (Adversarial) 5 Synthesizing Programs for Images using Reinforced Adversarial Learning	Transfer and Multi-Task Learning 2 Composable Planning with Attributes	Dimensionality Reduction 2 Representation Tradeoffs for Hyperbolic Embeddings	Online Learning 3 Let’s be Honest: An Optimal No-Regret Framework for Zero-Sum Games	Other Models and Methods 1 SAFFRON: an Adaptive Algorithm for Online Control of the False Discovery Rate
05:20 PM (Orals)			Autoregressive Convolutional Neural Networks for Asynchronous Time Series	Learning Compact Neural Networks with Regularization	Deep Variational Reinforcement Learning for POMDPs	Fast Bellman Updates for Robust MDPs		Distilling the Posterior in Bayesian Neural Networks	MAGAN: Aligning Biological Manifolds	Measuring abstract reasoning in neural networks	Massively Parallel Algorithms and Hardness for Single-Linkage Clustering under $\ell_p$ Distances	Weakly Consistent Optimal Pricing Algorithms in Repeated Posted-Price Auctions with Strategic Buyer	Open Category Detection with PAC Guarantees
05:30 PM (Orals)			Hierarchical Multi-Label Classification Networks	Riemannian Stochastic Recursive Gradient Algorithm with Retraction and Vector Transport and Its Convergence Analysis		Decoupling Gradient-Like Learning Rules from Representations		Bayesian Uncertainty Estimation for Batch Normalized Deep Networks	Max-Mahalanobis Linear Discriminant Analysis Networks			Self-Bounded Prediction Suffix Tree via Approximate String Matching	Unbiased Objective Estimation in Predictive Optimization
05:40 PM (Orals)			Nonparametric variable importance using an augmented neural network with multi-task learning	Low-Rank Riemannian Optimization on Positive Semidefinite Stochastic Matrices with Applications to Graph Clustering	Recurrent Predictive State Policy Networks	PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos		Noisy Natural Gradient as Variational Inference	Adversarial Time-to-Event Modeling	GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks	Local Density Estimation in High Dimensions	Spatio-temporal Bayesian On-line Changepoint Detection with Model Selection	Goodness-of-fit Testing for Discrete Distributions via Stein Discrepancy
05:50 PM (Orals)			Knowledge Transfer with Jacobian Matching	Graphical Nonconvex Optimization via an Adaptive Convex Relaxation	Regret Minimization for Partially Observable Deep Reinforcement Learning	Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learning		Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors	Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training	Explicit Inductive Bias for Transfer Learning with Convolutional Networks	Improving Sign Random Projections With Additional Information	Learning Localized Spatio-Temporal Models From Streaming Data	Towards Black-box Iterative Machine Teaching
06:15 PM (Posters)							Posters Thu
03:15 AM (Breaks)							Light Evening Snack
08:30 AM (Workshops)	Joint Workshop on AI in Health (day 1)	FCA4AI 2018												Fairness, Interpretability, and Explainability Federation of Workshops (day 1)	Towards learning with limited labels: Equivariance, Invariance, and Beyond	Linguistic and Cognitive Approaches To Dialog Agents (LaCATODA 2018)	The 3rd International workshop on biomedical informatics with optimization and machine learning (BOOM)	The 3rd International Workshop on Knowledge Discovery in Healthcare Data	6th Goal Reasoning Workshop	31st International Workshop on Qualitative Reasoning (QR 2018)	Autonomy in Teams -- Joint Workshop on Sharing Autonomy in Human-Robot Interaction	Computer Games Workshop	Tenth International Workshop Modelling and Reasoning in Context (MRC)

Time	Victoria	A9	A3	A1	A4	A7	K1	K11	A5	A6	K22
Fri Jul 13, 2018
09:30 AM (Orals)	Other Models and Methods 2 Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)	Optimization (Non-convex) 5 Convergence guarantees for a class of non-convex and non-smooth optimization problems	Time-Series Analysis 1 Learning Registered Point Processes from Idiosyncratic Observations	Reinforcement Learning 14 RLlib: Abstractions for Distributed Reinforcement Learning	Graphical Models 2 Learning in Integer Latent Variable Models with Nested Automatic Differentiation	Deep Learning (Adversarial) 6 Mixed batches and symmetric discriminators for GAN training	Computer Vision 2 Solving Partial Assignment Problems using Random Clique Complexes	Dimensionality Reduction 3 Out-of-sample extension of graph adjacency spectral embedding	Online Learning 4 Dynamic Regret of Strongly Adaptive Methods	Society Impacts of Machine Learning 2 A Reductions Approach to Fair Classification
09:50 AM (Orals)	Learning equations for extrapolation and control	A Progressive Batching L-BFGS Method for Machine Learning	Deep Bayesian Nonparametric Tracking	IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures	Sound Abstraction and Decomposition of Probabilistic Programs	Mutual Information Neural Estimation	Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction	Bayesian Model Selection for Change Point Detection and Clustering	Online Learning with Abstention	Probably Approximately Metric-Fair Learning
10:00 AM (Orals)	PDE-Net: Learning PDEs from Data				Parallel Bayesian Network Structure Learning	Adversarially Regularized Autoencoders	Video Prediction with Appearance and Motion Conditions	An Iterative, Sketching-based Framework for Ridge Regression	Multi-Fidelity Black-Box Optimization with Hierarchical Partitions
10:10 AM (Orals)	Transformation Autoregressive Networks	Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks	Learning Hidden Markov Models from Pairwise Co-occurrences with Application to Topic Modeling	Mix & Match - Agent Curricula for Reinforcement Learning	The Edge Density Barrier: Computational-Statistical Tradeoffs in Combinatorial Inference	JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets	Neural Program Synthesis from Diverse Demonstration Videos	Provable Variable Selection for Streaming Features	Adaptive Exploration-Exploitation Tradeoff for Opportunistic Bandits	Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
10:20 AM (Orals)	Weightless: Lossy weight encoding for deep neural network compression	Estimation of Markov Chain via Rank-constrained Likelihood		Learning to Explore via Meta-Policy Gradient	Temporal Poisson Square Root Graphical Models	Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data		Learning Low-Dimensional Temporal Representations	Firing Bandits: Optimizing Crowdfunding	Blind Justice: Fairness with Encrypted Sensitive Attributes
11:00 AM (Orals)	Deep Learning (Neural Network Architectures) 11 Efficient Neural Audio Synthesis	Optimization (Convex) 5 A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming	Transfer and Multi-Task Learning 3 Learning Adversarially Fair and Transferable Representations	Reinforcement Learning 15 Hierarchical Imitation and Reinforcement Learning	Gaussian Processes 3 Scalable Gaussian Processes with Grid-Structured Eigenfunctions (GP-GRIEF)	Generative Models 3 Junction Tree Variational Autoencoder for Molecular Graph Generation	Deep Learning (Theory) 6 Spurious Local Minima are Common in Two-Layer ReLU Neural Networks	Optimization (Combinatorial) 4 Competitive Caching with Machine Learned Advice	Online Learning 5 Online Linear Quadratic Control	Unsupervised Learning 2 Theoretical Analysis of Sparse Subspace Clustering with Missing Entries
11:20 AM (Orals)	Understanding and Simplifying One-Shot Architecture Search	Frank-Wolfe with Subsampling Oracle	Learning Semantic Representations for Unsupervised Domain Adaptation	Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning	State Space Gaussian Processes with Non-Gaussian Likelihood	Semi-Amortized Variational Autoencoders	Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks	Distributed Clustering via LSH Based Data Partitioning	Semiparametric Contextual Bandits	Improved nearest neighbor search using auxiliary information and priority functions
11:30 AM (Orals)			CyCADA: Cycle-Consistent Adversarial Domain Adaptation					Learning to Branch		QuantTree: Histograms for Change Detection in Multivariate Data Streams
11:40 AM (Orals)	Path-Level Network Transformation for Efficient Architecture Search	On Matching Pursuit and Coordinate Descent	Rectify Heterogeneous Models with Semantic Mapping	State Abstractions for Lifelong Reinforcement Learning	Constant-Time Predictive Distributions for Gaussian Processes	Iterative Amortized Inference	On the Power of Over-parametrization in Neural Networks with Quadratic Activation	Compiling Combinatorial Prediction Games	Minimax Concave Penalized Multi-Armed Bandit Model with High-Dimensional Covariates	Topological mixture estimation
11:50 AM (Orals)	Learning Longer-term Dependencies in RNNs with Auxiliary Losses	Adaptive Three Operator Splitting	Detecting and Correcting for Label Shift with Black Box Predictors	Policy Optimization with Demonstrations	Large-Scale Cox Process Inference using Variational Fourier Features	DVAE++: Discrete Variational Autoencoders with Overlapping Transformations	Optimization Landscape and Expressivity of Deep CNNs	Approximation Algorithms for Cascading Prediction Models	Racing Thompson: an Efficient Algorithm for Thompson Sampling with Non-conjugate Priors	Revealing Common Statistical Behaviors in Heterogeneous Populations
01:30 PM (Invited Talks)				Language to Action: towards Interactive Task Learning with Physical Agents
02:00 PM (Workshops)											Learning and Reasoning: Principles & Applications to Everyday Spatial and Temporal Knowledge (day 1)
02:30 PM (Invited Talks)				Building Machines that Learn and Think Like People
04:00 PM (Orals)	Deep Learning (Neural Network Architectures) 12 Progress & Compress: A scalable framework for continual learning	Optimization (Convex) 6 SADAGRAD: Strongly Adaptive Stochastic Gradient Methods	Parallel and Distributed Learning 3 The Hidden Vulnerability of Distributed Learning in Byzantium	Reinforcement Learning 16 Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator	Monte Carlo Methods 2 Stein Variational Gradient Descent Without Gradient	Generative Models 4 Parallel WaveNet: Fast High-Fidelity Speech Synthesis	Deep Learning (Theory) 7 Efficient end-to-end learning for quantizable representations	Spectral Methods 1 On the Spectrum of Random Features Maps of High Dimensional Data	Causal Inference 1 Causal Bandits with Propagating Inference	Supervised Learning 3 Candidates vs. Noises Estimation for Large Multi-Class Classification Problem

Tue Jul 10, 2018

Wed Jul 11, 2018

Thu Jul 12, 2018

Fri Jul 13, 2018