Downloads 2018
Number of events: 709
- $D^2$: Decentralized Training over Decentralized Data
- 10th International Workshop on Agents in Traffic and Transportation (ATT 2018)
- 19th International Workshop on Multi-Agent-Based Simulation (MABS 2018)
- 2nd International Joint Conference on Artificial Intelligence (IJCAI) Workshop on Artificial Intelligence in Affective Computing
- 31st International Workshop on Qualitative Reasoning (QR 2018)
- 6th Goal Reasoning Workshop
- ABMUS-18 - Agent-Based Modelling of Urban Systems
- A Boo(n) for Evaluating Architecture Performance
- Accelerated Spectral Ranking
- Accelerating Greedy Coordinate Descent Methods
- Accelerating Natural Gradient with Higher-Order Invariance
- Accurate Inference for Adaptive Linear Models
- Accurate Uncertainties for Deep Learning Using Calibrated Regression
- A Classification-Based Study of Covariate Shift in GAN Distributions
- A Conditional Gradient Framework for Composite Convex Minimization with Applications to Semidefinite Programming
- Active Learning with Logged Data
- Active Testing: An Efficient and Robust Framework for Estimating Accuracy
- Adafactor: Adaptive Learning Rates with Sublinear Memory Cost
- Adaptive and Learning Agents 2018 (day 1)
- Adaptive and Learning Agents 2018 (day 2)
- Adaptive Exploration-Exploitation Tradeoff for Opportunistic Bandits
- Adaptive Sampled Softmax with Kernel Based Sampling
- Adaptive Three Operator Splitting
- Addressing Function Approximation Error in Actor-Critic Methods
- A Delay-tolerant Proximal-Gradient Algorithm for Distributed Learning
- A Distributed Second-Order Algorithm You Can Trust
- ADMM and Accelerated ADMM as Continuous Dynamical Systems
- Adversarial Attack on Graph Structured Data
- Adversarial Learning with Local Coordinate Coding
- Adversarially Regularized Autoencoders
- Adversarial Regression with Multiple Learners
- Adversarial Risk and the Dangers of Evaluating Against Weak Attacks
- Adversarial Time-to-Event Modeling
- A Fast and Scalable Joint Estimator for Integrating Additional Knowledge in Learning Multiple Related Sparse Gaussian Graphical Models
- A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music
- AI and Computational Psychology: Theories, Algorithms and Applications (CompPsy)
- AI and Security: Lessons, Challenges and Future Directions
- AI for Aging, Rehabilitation and Independent Assisted Living (ARIAL) and Intelligent Conversation Agents in Home and Geriatric Care Applications
- AI for Synthetic Biology 2
- AI-MHRI (AI for Multimodal Human-Robot Interaction) (day 1)
- AI-MHRI (AI for Multimodal Human-Robot Interaction) (day 2)
- ALAW - Agents Living in Augmented Worlds
- Alternating Randomized Block Coordinate Descent
- An Algorithmic Framework of Variable Metric Over-Relaxed Hybrid Proximal Extra-Gradient Method
- An Alternative View: When Does SGD Escape Local Minima?
- Analysis of Minimax Error Rate for Crowdsourcing and Its Application to Worker Clustering Model
- Analyzing the Robustness of Nearest Neighbors to Adversarial Examples
- Analyzing Uncertainty in Neural Machine Translation
- An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning
- An Efficient Semismooth Newton based Algorithm for Convex Clustering
- An Estimation and Analysis Framework for the Rasch Model
- An Inference-Based Policy Gradient Method for Learning Options
- An Iterative, Sketching-based Framework for Ridge Regression
- Anonymous Walk Embeddings
- An Optimal Control Approach to Deep Learning and Applications to Discrete-Weight Neural Networks
- Approximate Leave-One-Out for Fast Parameter Tuning in High Dimensions
- Approximate message passing for amplitude based optimization
- Approximation Algorithms for Cascading Prediction Models
- Approximation Guarantees for Adaptive Sampling
- A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery
- A probabilistic framework for multi-view feature learning with many-to-many associations via neural networks
- A Probabilistic Theory of Supervised Similarity Learning for Pointwise ROC Curve Optimization
- A Progressive Batching L-BFGS Method for Machine Learning
- Architectures and Evaluation for Generality, Autonomy and Progress in AI (AEGAP)
- A Reductions Approach to Fair Classification
- A Robust Approach to Sequential Information Theoretic Planning
- Artificial Intelligence for Knowledge Management
- Artificial Intelligence for Wildlife Conservation (AIWC) Workshop
- A Semantic Loss Function for Deep Learning with Symbolic Knowledge
- A Simple Stochastic Variance Reduced Algorithm with Fast Convergence Rates
- A Spectral Approach to Gradient Estimation for Implicit Distributions
- A Spline Theory of Deep Learning
- Asynchronous Byzantine Machine Learning (the case of SGD)
- Asynchronous Decentralized Parallel Stochastic Gradient Descent
- Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization
- A Theoretical Explanation for Perplexing Behaviors of Backpropagation-based Visualizations
- Attention-based Deep Multiple Instance Learning
- A Two-Step Computation of the Exact GAN Wasserstein Distance
- Augment and Reduce: Stochastic Inference for Large Categorical Distributions
- Augmented CycleGAN: Learning Many-to-Many Mappings from Unpaired Data
- A Unified Framework for Structured Low-rank Matrix Learning
- Automatic Goal Generation for Reinforcement Learning Agents
- AutoML 2018
- Autonomy in Teams -- Joint Workshop on Sharing Autonomy in Human-Robot Interaction
- AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning
- Autoregressive Convolutional Neural Networks for Asynchronous Time Series
- Autoregressive Quantile Networks for Generative Modeling
- Bandits with Delayed, Aggregated Anonymous Feedback
- Batch Bayesian Optimization via Multi-objective Acquisition Ensemble for Automated Analog Circuit Design
- Bayesian Coreset Construction via Greedy Iterative Geodesic Ascent
- Bayesian Model Selection for Change Point Detection and Clustering
- Bayesian Optimization of Combinatorial Structures
- Bayesian Quadrature for Multiple Related Integrals
- Bayesian Uncertainty Estimation for Batch Normalized Deep Networks
- Been There, Done That: Meta-Learning with Episodic Recall
- Best Arm Identification in Linear Bandits with Linear Dimension Dependency
- Beyond 1/2-Approximation for Submodular Maximization on Massive Data Streams
- Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations
- Beyond the One-Step Greedy Approach in Reinforcement Learning
- Bilevel Programming for Hyperparameter Optimization and Meta-Learning
- Binary Classification with Karmic, Threshold-Quasi-Concave Metrics
- Binary Partitions with Approximate Minimum Impurity
- Black-box Adversarial Attacks with Limited Queries and Information
- Black Box FDR
- Black-Box Variational Inference for Stochastic Differential Equations
- Blind Justice: Fairness with Encrypted Sensitive Attributes
- BOCK : Bayesian Optimization with Cylindrical Kernels
- BOHB: Robust and Efficient Hyperparameter Optimization at Scale
- Born Again Neural Networks
- Bounding and Counting Linear Regions of Deep Neural Networks
- Bounds on the Approximation Power of Feedforward Neural Networks
- Bridging the Gap between Human and Automated Reasoning
- Bucket Renormalization for Approximate Inference
- Budgeted Experiment Design for Causal Structure Learning
- Building Machines that Learn and Think Like People
- Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
- Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games?
- Candidates vs. Noises Estimation for Large Multi-Class Classification Problem
- Canonical Tensor Decomposition for Knowledge Base Completion
- Causal Bandits with Propagating Inference
- Celer: a Fast Solver for the Lasso with Dual Extrapolation
- Characterizing and Learning Equivalence Classes of Causal DAGs under Interventions
- Characterizing Implicit Bias in Terms of Optimization Geometry
- Chi-square Generative Adversarial Network
- Classification from Pairwise Similarity and Unlabeled Data
- Clipped Action Policy Gradient
- Closed-form Marginal Likelihood in Gamma-Poisson Matrix Factorization
- Clustering Semi-Random Mixtures of Gaussians
- Coded Sparse Matrix Multiplication
- Cognitive Vision: Integrated Vision and AI for Embodied Perception and Interaction
- Communication-Computation Efficient Gradient Coding
- Comparing Dynamics: Deep Neural Networks versus Glassy Systems
- Comparison-Based Random Forests
- Competitive Caching with Machine Learned Advice
- Competitive Multi-agent Inverse Reinforcement Learning with Sub-optimal Demonstrations
- Compiling Combinatorial Prediction Games
- Composable Planning with Attributes
- Composite Functional Gradient Learning of Generative Adversarial Models
- Composite Marginal Likelihood Methods for Random Utility Models
- Compressing Neural Networks using the Variational Information Bottelneck
- Computational Optimal Transport: Complexity by Accelerated Gradient Descent Is Better Than by Sinkhorn's Algorithm
- Computer Games Workshop
- Conditional Neural Processes
- Conditional Noise-Contrastive Estimation of Unnormalised Models
- Configurable Markov Decision Processes
- Constant-Time Predictive Distributions for Gaussian Processes
- Constrained Interacting Submodular Groupings
- Constraining the Dynamics of Deep Probabilistic Models
- ContextNet: Deep learning for Star Galaxy Classification
- Contextual Graph Markov Model: A Deep and Generative Approach to Graph Processing
- Continual Reinforcement Learning with Complex Synapses
- Continuous and Discrete-time Accelerated Stochastic Mirror Descent for Strongly Convex Functions
- Continuous-Time Flows for Efficient Inference and Density Estimation
- Convergence guarantees for a class of non-convex and non-smooth optimization problems
- Convergent Tree Backup and Retrace with Function Approximation
- Convolutional Imputation of Matrix Networks
- Coordinated Exploration in Concurrent Reinforcement Learning
- Covariate Adjusted Precision Matrix Estimation via Nonconvex Optimization
- CoVeR: Learning Covariate-Specific Vector Representations with Tensor Decompositions
- CRAFTML, an Efficient Clustering-based Random Forest for Extreme Multi-label Learning
- Crowdsourcing with Arbitrary Adversaries
- CRVI: Convex Relaxation for Variational Inference
- Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks
- Cut-Pursuit Algorithm for Regularizing Nonsmooth Functionals with Graph Total Variation
- CyCADA: Cycle-Consistent Adversarial Domain Adaptation
- Data-Dependent Stability of Stochastic Gradient Descent
- Data Science meets Optimization
- Data Summarization at Scale: A Two-Stage Submodular Approach
- DCFNet: Deep Neural Network with Decomposed Convolutional Filters
- Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings
- Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
- Decoupled Parallel Backpropagation with Convergence Guarantee
- Decoupling Gradient-Like Learning Rules from Representations
- Deep Asymmetric Multi-task Feature Learning
- Deep Bayesian Nonparametric Tracking
- Deep Density Destructors
- Deep k-Means: Re-Training and Parameter Sharing with Harder Cluster Assignments for Compressing Deep Convolutions
- Deep Linear Networks with Arbitrary Loss: All Local Minima Are Global
- Deep Models of Interactions Across Sets
- Deep One-Class Classification
- Deep Predictive Coding Network for Object Recognition
- Deep Reinforcement Learning in Continuous Action Spaces: a Case Study in the Game of Simulated Curling
- Deep Variational Reinforcement Learning for POMDPs
- Defining and Designing Fair Algorithms
- Delayed Impact of Fair Machine Learning
- Dependent Relational Gamma Process Models for Longitudinal Networks
- Design of Experiments for Model Discrimination Hybridising Analytical and Data-Driven Approaches
- Detecting and Correcting for Label Shift with Black Box Predictors
- Detecting non-causal artifacts in multivariate linear regression models
- DiCE: The Infinitely Differentiable Monte Carlo Estimator
- DICOD: Distributed Convolutional Coordinate Descent for Convolutional Sparse Coding
- Differentiable Abstract Interpretation for Provably Robust Neural Networks
- Differentiable Compositional Kernel Learning for Gaussian Processes
- Differentiable Dynamic Programming for Structured Prediction and Attention
- Differentiable plasticity: training plastic neural networks with backpropagation
- Differentially Private Database Release via Kernel Mean Embeddings
- Differentially Private Identity and Equivalence Testing of Discrete Distributions
- Differentially Private Matrix Completion Revisited
- Dimensionality-Driven Learning with Noisy Labels
- Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learning
- Discovering Interpretable Representations for Both Deep Generative and Discriminative Models
- Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms
- Disentangled Sequential Autoencoder
- Disentangling by Factorising
- Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients
- Dissipativity Theory for Accelerating Stochastic Variance Reduction: A Unified Analysis of SVRG and Katyusha Using Semidefinite Programs
- Distilling the Posterior in Bayesian Neural Networks
- Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go?
- Distributed Clustering via LSH Based Data Partitioning
- Distributed Nonparametric Regression under Communication Constraints
- Does Distributionally Robust Supervised Learning Give Robust Classifiers?
- Domain Adaptation for Visual Understanding
- Do Outliers Ruin Collaboration?
- DRACO: Byzantine-resilient Distributed Training via Redundant Gradients
- Dropout Training, Data-dependent Regularization, and Generalization Bounds
- DVAE++: Discrete Variational Autoencoders with Overlapping Transformations
- Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networks
- Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks
- Dynamic Evaluation of Neural Sequence Models
- Dynamic Regret of Strongly Adaptive Methods
- Efficient and Consistent Adversarial Bipartite Matching
- Efficient Bias-Span-Constrained Exploration-Exploitation in Reinforcement Learning
- Efficient end-to-end learning for quantizable representations
- Efficient First-Order Algorithms for Adaptive Signal Denoising
- Efficient Gradient-Free Variational Inference using Policy Search
- Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation
- Efficient Neural Architecture Search via Parameters Sharing
- Efficient Neural Audio Synthesis
- Eighth International Workshop on Statistical Relational AI
- Enabling Reproducibility in Machine Learning MLTrain@RML
- End-to-end Active Object Tracking via Reinforcement Learning
- End-to-End Learning for the Deep Multivariate Probit Model
- Engineering Multi-Agent Systems (day 1)
- Engineering Multi-Agent Systems (day 2)
- Entropy-SGD optimizes the prior of a PAC-Bayes bound: Generalization properties of Entropy-SGD and data-dependent priors
- Equivalence of Multicategory SVM and Simplex Cone SVM: Fast Computations and Statistical Theory
- Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization
- Error Estimation for Randomized Least-Squares Algorithms via the Bootstrap
- Escaping Saddles with Stochastic Gradients
- Essentially No Barriers in Neural Network Energy Landscape
- Estimation of Markov Chain via Rank-constrained Likelihood
- Explicit Inductive Bias for Transfer Learning with Convolutional Networks
- Exploiting the Potential of Standard Convolutional Autoencoders for Image Restoration by Evolutionary Search
- Exploration in Reinforcement Learning
- Exploring Hidden Dimensions in Accelerating Convolutional Neural Networks
- Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples
- Extreme Learning to Rank via Low Rank Assumption
- Fair and Diverse DPP-Based Data Summarization
- Fairness, Interpretability, and Explainability Federation of Workshops (day 1)
- Fairness, Interpretability, and Explainability Federation of Workshops (day 2-3) (day 1)
- Fairness, Interpretability, and Explainability Federation of Workshops (day 2-3) (day 2)
- Fairness Without Demographics in Repeated Loss Minimization
- Fast and Sample Efficient Inductive Matrix Completion via Multi-Phase Procrustes Flow
- Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam
- Fast Approximate Spectral Clustering for Dynamic Networks
- Fast Bellman Updates for Robust MDPs
- Fast Decoding in Sequence Models Using Discrete Latent Variables
- Faster Derivative-Free Stochastic Algorithm for Shared Memory Machines
- Fast Gradient-Based Methods with Exponential Rate: A Hybrid Control Framework
- Fast Information-theoretic Bayesian Optimisation
- Fast Maximization of Non-Submodular, Monotonic Functions on the Integer Lattice
- Fast Parametric Learning with Activation Memorization
- Fast Stochastic AUC Maximization with $O(1/n)$-Convergence Rate
- Fast Variance Reduction Method with Stochastic Batch Size
- FCA4AI 2018
- Feasible Arm Identification
- Federated AI for Robotics Workshop (F-Rob-2018)
- Feedback-Based Tree Search for Reinforcement Learning
- Finding Influential Training Samples for Gradient Boosted Decision Trees
- Firing Bandits: Optimizing Crowdfunding
- First international workshop on socio-cognitive systems
- First Order Generative Adversarial Networks
- First Workshop on Deep Learning for Safety-Critical in Engineering Systems
- Fitting New Speakers Based on a Short Untranscribed Sample
- Fixing a Broken ELBO
- Focused Hierarchical RNNs for Conditional Sequence Processing
- Fourier Policy Gradients
- Frank-Wolfe with Subsampling Oracle
- Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents
- Functional Gradient Boosting based on Residual Network Perception
- GAIN: Missing Data Imputation using Generative Adversarial Nets
- Game-Theoretic Mechanisms for Data and Information
- Gated Path Planning Networks
- Generalization without Systematicity: On the Compositional Skills of Sequence-to-Sequence Recurrent Networks
- Generalized Earley Parser: Bridging Symbolic Grammars and Sequence Data for Future Prediction
- Generalized Robust Bayesian Committee Machine for Large-scale Gaussian Process Regression
- Generative Temporal Models with Spatial Memory for Partially Observed Environments
- Geodesic Convolutional Shape Optimization
- Geometry in Machine Learning (GiMLi)
- Geometry Score: A Method For Comparing Generative Adversarial Networks
- GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms
- Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator
- Goal Specifications for Reinforcement Learning
- Goodness-of-fit Testing for Discrete Distributions via Stein Discrepancy
- Gradient-Based Meta-Learning with Learned Layerwise Metric and Subspace
- Gradient Coding from Cyclic MDS Codes and Expander Graphs
- Gradient Descent for Sparse Rank-One Matrix Completion for Crowd-Sourced Aggregation of Sparsely Interacting Workers
- Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima
- Gradient descent with identity initialization efficiently learns positive definite linear transformations by deep residual networks
- Gradient Primal-Dual Algorithm Converges to Second-Order Stationary Solution for Nonconvex Distributed Optimization Over Networks
- GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks
- Gradually Updated Neural Networks for Large-Scale Image Recognition
- Graphical Nonconvex Optimization via an Adaptive Convex Relaxation
- Graph Networks as Learnable Physics Engines for Inference and Control
- GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
- Greed is Still Good: Maximizing Monotone Submodular+Supermodular (BP) Functions
- Hierarchical Clustering with Structural Constraints
- Hierarchical Deep Generative Models for Multi-Rate Multivariate Time Series
- Hierarchical Imitation and Reinforcement Learning
- Hierarchical Long-term Video Prediction without Supervision
- Hierarchical Multi-Label Classification Networks
- Hierarchical Text Generation and Planning for Strategic Dialogue
- High Performance Zero-Memory Overhead Direct Convolutions
- High-Quality Prediction Intervals for Deep Learning: A Distribution-Free, Ensembled Approach
- Humanizing AI (HAI)
- Hyperbolic Entailment Cones for Learning Hierarchical Embeddings
- Image Transformer
- Imitation Learning
- IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
- Implicit Quantile Networks for Distributional Reinforcement Learning
- Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval and Matrix Completion
- Importance Weighted Transfer of Samples in Reinforcement Learning
- Improved large-scale graph learning through ridge spectral sparsification
- Improved nearest neighbor search using auxiliary information and priority functions
- Improved Regret Bounds for Thompson Sampling in Linear Quadratic Control Problems
- Improved Training of Generative Adversarial Networks Using Representative Features
- Improving Optimization in Models With Continuous Symmetry Breaking
- Improving Regression Performance with Distributional Losses
- Improving Sign Random Projections With Additional Information
- Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising
- Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms
- Inductive Two-Layer Modeling with Parametric Bregman Transfer
- Inference Suboptimality in Variational Autoencoders
- Information Theoretic Guarantees for Empirical Risk Minimization with Applications to Model Selection and Large-Scale Optimization
- INSPECTRE: Privately Estimating the Unseen
- Intelligence per Kilowatthour
- Inter and Intra Topic Structure Learning with Word Embeddings
- International Workshop on Automated Negotiation (ACAN)
- International Workshop on Massively Multi-Agent Systems
- International Workshop on Optimization in Multi-Agent Systems (OptMAS)
- International Workshop on Real Time compliant Multi-Agent Systems (RTcMAS)
- Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)
- Invariance of Weight Distributions in Rectified MLPs
- Investigating Human Priors for Playing Video Games
- Is Generator Conditioning Causally Related to GAN Performance?
- Iterative Amortized Inference
- JointGAN: Multi-Domain Joint Distribution Learning with Generative Adversarial Nets
- Joint ICML and IJCAI Workshop on Computational Biology 2018
- Joint Workshop on AI in Health (day 1)
- Joint Workshop on AI in Health (day 2)
- Joint Workshop on Multimedia for Cooking and Eating Activities and Multimedia Assisted Dietary Management (CEA/MADiMa2018)
- Junction Tree Variational Autoencoder for Molecular Graph Generation
- Katyusha X: Simple Momentum Method for Stochastic Sum-of-Nonconvex Optimization
- K-Beam Minimax: Efficient Optimization for Deep Adversarial Learning
- Kernelized Synaptic Weight Matrices
- Kernel Recursive ABC: Point Estimation with Intractable Likelihood
- K-means clustering using random matrix sparsification
- Knowledge Transfer with Jacobian Matching
- Kronecker Recurrent Units
- Language to Action: towards Interactive Task Learning with Physical Agents
- Large-Scale Cox Process Inference using Variational Fourier Features
- Large-Scale Sparse Inverse Covariance Estimation via Thresholding and Max-Det Matrix Completion
- Latent Space Policies for Hierarchical Reinforcement Learning
- LaVAN: Localized and Visible Adversarial Noise
- LeapsAndBounds: A Method for Approximately Optimal Algorithm Configuration
- Learn from Your Neighbor: Learning Multi-modal Mappings from Sparse Annotations
- Learning Adversarially Fair and Transferable Representations
- Learning a Mixture of Two Multinomial Logits
- Learning and Memorization
- Learning and Reasoning: Principles & Applications to Everyday Spatial and Temporal Knowledge (day 1)
- Learning and Reasoning: Principles & Applications to Everyday Spatial and Temporal Knowledge (day 2)
- Learning Binary Latent Variable Models: A Tensor Eigenpair Approach
- Learning by Playing - Solving Sparse Reward Tasks from Scratch
- Learning Compact Neural Networks with Regularization
- Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry
- Learning Deep ResNet Blocks Sequentially using Boosting Theory
- Learning Diffusion using Hyperparameters
- Learning Dynamics of Linear Denoising Autoencoders
- Learning equations for extrapolation and control
- Learning Hidden Markov Models from Pairwise Co-occurrences with Application to Topic Modeling
- Learning Implicit Generative Models with the Method of Learned Moments
- Learning Independent Causal Mechanisms
- Learning in Integer Latent Variable Models with Nested Automatic Differentiation
- Learning in Reproducing Kernel Kreı̆n Spaces
- Learning K-way D-dimensional Discrete Codes for Compact Embedding Representations
- Learning Localized Spatio-Temporal Models From Streaming Data
- Learning Longer-term Dependencies in RNNs with Auxiliary Losses
- Learning long term dependencies via Fourier recurrent units
- Learning Low-Dimensional Temporal Representations
- Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time
- Learning Memory Access Patterns
- Learning One Convolutional Layer with Overlapping Patches
- Learning Policy Representations in Multiagent Systems
- Learning Registered Point Processes from Idiosyncratic Observations
- Learning Representations and Generative Models for 3D Point Clouds
- Learning Semantic Representations for Unsupervised Domain Adaptation
- Learning Steady-States of Iterative Algorithms over Graphs
- Learning the Reward Function for a Misspecified Model
- Learning to Act in Decentralized Partially Observable MDPs
- Learning to Branch
- Learning to Coordinate with Coordination Graphs in Repeated Single-Stage Multi-Agent Decision Problems
- Learning to Explain: An Information-Theoretic Perspective on Model Interpretation
- Learning to Explore via Meta-Policy Gradient
- Learning to Optimize Combinatorial Functions
- Learning to Reweight Examples for Robust Deep Learning
- Learning to search with MCTSnets
- Learning to Speed Up Structured Output Prediction
- Learning unknown ODE models with Gaussian processes
- Learning with Abandonment
- Learning with Temporal Point Processes
- Least-Squares Temporal Difference Learning for the Linear Quadratic Regulator
- Let’s be Honest: An Optimal No-Regret Framework for Zero-Sum Games
- Level-Set Methods for Finite-Sum Constrained Convex Optimization
- Leveraging Well-Conditioned Bases: Streaming and Distributed Summaries in Minkowski $p$-Norms
- Lifelong Learning: A Reinforcement Learning Approach
- Lightweight Stochastic Optimization for Minimizing Finite Sums with Infinite Data
- Limits of Estimating Heterogeneous Treatment Effects: Guidelines for Practical Algorithm Design
- Linear Spectral Estimators and an Application to Phase Retrieval
- Linguistic and Cognitive Approaches To Dialog Agents (LaCATODA 2018)
- Lipschitz Continuity in Model-based Reinforcement Learning
- Local Convergence Properties of SAGA/Prox-SVRG and Acceleration
- Local Density Estimation in High Dimensions
- Locally Private Hypothesis Testing
- Local Private Hypothesis Testing: Chi-Square Tests
- Loss Decomposition for Fast Learning in Large Output Spaces
- Low-Rank Riemannian Optimization on Positive Semidefinite Stochastic Matrices with Applications to Graph Clustering
- Lyapunov Functions for First-Order Methods: Tight Automated Convergence Guarantees
- Machine learning for Causal Inference, Counterfactual Prediction, and Autonomous Action (CausalML)
- Machine Learning for Personalised Health
- Machine Learning in Automated Mechanism Design for Pricing and Auctions
- Machine Learning: The Debates
- Machine Theory of Mind
- MAGAN: Aligning Biological Manifolds
- Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits
- Markov Modulated Gaussian Cox Processes for Semi-Stationary Intensity Modeling of Events Data
- Massively Parallel Algorithms and Hardness for Single-Linkage Clustering under $\ell_p$ Distances
- Matrix Norms in Data Streams: Faster, Multi-Pass and Row-Order
- Max-Mahalanobis Linear Discriminant Analysis Networks
- Mean Field Multi-Agent Reinforcement Learning
- Measuring abstract reasoning in neural networks
- MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels
- Message Passing Stein Variational Gradient Descent
- Meta-Learning by Adjusting Priors Based on Extended PAC-Bayes Theory
- Minibatch Gibbs Sampling on Large Graphical Models
- Minimal I-MAP MCMC for Scalable Structure Discovery in Causal DAG Models
- Minimax Concave Penalized Multi-Armed Bandit Model with High-Dimensional Covariates
- Mitigating Bias in Adaptive Data Gathering via Differential Privacy
- Mixed batches and symmetric discriminators for GAN training
- Mix & Match - Agent Curricula for Reinforcement Learning
- Modeling Others using Oneself in Multi-Agent Reinforcement Learning
- Modeling Sparse Deviations for Compressed Sensing using Generative Models
- Model-Level Dual Learning
- Modern Trends in Nonconvex Optimization for Machine Learning
- More Robust Doubly Robust Off-policy Evaluation
- MSplit LBI: Realizing Feature Selection and Dense Estimation Simultaneously in Few-shot and Zero-shot Learning
- Multicalibration: Calibration for the (Computationally-Identifiable) Masses
- Multi-Fidelity Black-Box Optimization with Hierarchical Partitions
- Mutual Information Neural Estimation
- Nearly Optimal Robust Subspace Tracking
- Near Optimal Frequent Directions for Sketching Dense and Sparse Matrices
- NetGAN: Generating Graphs via Random Walks
- Network Global Testing by Counting Graphlets
- Neural Abstract Machines & Program Induction Workshop v2.0 (NAMPI_v2)
- Neural Autoregressive Flows
- Neural Dynamic Programming for Musical Self Similarity
- Neural Inverse Rendering for General Reflectance Photometric Stereo
- Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions
- Neural Program Synthesis from Diverse Demonstration Videos
- Neural Relational Inference for Interacting Systems
- Noise2Noise: Learning Image Restoration without Clean Data
- Noisin: Unbiased Regularization for Recurrent Neural Networks
- Noisy Natural Gradient as Variational Inference
- Non-convex Conditional Gradient Sliding
- Nonconvex Optimization for Regression with Fairness Constraints
- Non-linear motor control by local learning in spiking neural networks
- Nonoverlap-Promoting Variable Selection
- Nonparametric Regression with Comparisons: Escaping the Curse of Dimensionality with Ordinal Information
- Nonparametric variable importance using an augmented neural network with multi-task learning
- Not All Samples Are Created Equal: Deep Learning with Importance Sampling
- Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care
- Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples
- oi-VAE: Output Interpretable VAEs for Nonlinear Group Factor Analysis
- On Acceleration with Noise-Corrupted Gradients
- One-Shot Segmentation in Clutter
- On Learning Sparsely Used Dictionaries from Incomplete Samples
- Online Convolutional Sparse Coding with Sample-Dependent Dictionary
- Online Learning with Abstention
- Online Linear Quadratic Control
- On Matching Pursuit and Coordinate Descent
- On Nesting Monte Carlo Estimators
- On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
- On the Implicit Bias of Dropout
- On the Limitations of First-Order Approximation in GAN Dynamics
- On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization
- On the Power of Over-parametrization in Neural Networks with Quadratic Activation
- On the Relationship between Data Efficiency and Error for Uncertainty Sampling
- On the Spectrum of Random Features Maps of High Dimensional Data
- On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo
- Open Category Detection with PAC Guarantees
- Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods
- Optimal Rates of Sketched-regularized Algorithms for Least-Squares Regression over Hilbert Spaces
- Optimal Tuning for Divide-and-conquer Kernel Ridge Regression with Massive Data
- Optimization, fast and slow: optimally switching between local and Bayesian optimization
- Optimization Landscape and Expressivity of Deep CNNs
- Optimization Perspectives on Learning to Control
- Optimizing the Latent Space of Generative Networks
- Orthogonality-Promoting Distance Metric Learning: Convex Relaxation and Theoretical Analysis
- Orthogonal Machine Learning: Power and Limitations
- Orthogonal Recurrent Neural Networks with Scaled Cayley Transform
- Out-of-sample extension of graph adjacency spectral embedding
- Overcoming Catastrophic Forgetting with Hard Attention to the Task
- Parallel and Streaming Algorithms for K-Core Decomposition
- Parallel Bayesian Network Structure Learning
- Parallel WaveNet: Fast High-Fidelity Speech Synthesis
- Parameterized Algorithms for the Matrix Completion Problem
- Partial Optimality and Fast Lower Bounds for Weighted Correlation Clustering
- Path Consistency Learning in Tsallis Entropy Regularized MDPs
- Path-Level Network Transformation for Efficient Architecture Search
- Pathwise Derivatives Beyond the Reparameterization Trick
- PDE-Net: Learning PDEs from Data
- PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos
- PixelSNAIL: An Improved Autoregressive Generative Model
- Planning and Learning (PAL-18)
- Policy and Value Transfer in Lifelong Reinforcement Learning
- Policy Optimization as Wasserstein Gradient Flows
- Policy Optimization with Demonstrations
- Practical Contextual Bandits with Regression Oracles
- prDeep: Robust Phase Retrieval with a Flexible Deep Network
- Predict and Constrain: Modeling Cardinality in Deep Structured Prediction
- Prediction and Generative Modeling in Reinforcement Learning
- Prediction Rule Reshaping
- PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning
- Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness
- Privacy in Machine Learning and Artificial Intelligence (PiMLAI)
- Probabilistic Boolean Tensor Decomposition
- Probabilistic Recurrent State-Space Models
- Probably Approximately Metric-Fair Learning
- Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs
- Programmatically Interpretable Reinforcement Learning
- Progress & Compress: A scalable framework for continual learning
- Projection-Free Online Optimization with Stochastic Gradient: From Convexity to Submodularity
- Proportional Allocation: Simple, Distributed, and Diverse Matching with High Entropy
- Provable Defenses against Adversarial Examples via the Convex Outer Adversarial Polytope
- Provable Variable Selection for Streaming Features
- Pseudo-task Augmentation: From Deep Multitask Learning to Intratask Sharing—and Back
- QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
- QuantTree: Histograms for Change Detection in Multivariate Data Streams
- Quasi-Monte Carlo Variational Inference
- Quickshift++: Provably Good Initializations for Sample-Based Mean Shift
- Racing Thompson: an Efficient Algorithm for Thompson Sampling with Non-conjugate Priors
- RadialGAN: Leveraging multiple datasets to improve target-specific predictive models using Generative Adversarial Networks
- Randomized Block Cubic Newton Method
- Ranking Distributions based on Noisy Sorting
- Rapid Adaptation with Conditionally Shifted Neurons
- Rates of Convergence of Spectral Methods for Graphon Estimation
- Rectify Heterogeneous Models with Semantic Mapping
- Recurrent Predictive State Policy Networks
- Regret Minimization for Partially Observable Deep Reinforcement Learning
- Reinforcement Learning with Function-Valued Action Spaces for Partial Differential Equation Control
- Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training
- Representation Learning on Graphs with Jumping Knowledge Networks
- Representation Tradeoffs for Hyperbolic Embeddings
- Residual Unfairness in Fair Machine Learning from Prejudiced Data
- Revealing Common Statistical Behaviors in Heterogeneous Populations
- Reviving and Improving Recurrent Back-Propagation
- Riemannian Stochastic Recursive Gradient Algorithm with Retraction and Vector Transport and Its Convergence Analysis
- RLlib: Abstractions for Distributed Reinforcement Learning
- Robust and Scalable Models of Microbiome Dynamics
- SADAGRAD: Strongly Adaptive Stochastic Gradient Methods
- Safe Element Screening for Submodular Function Minimization
- SAFFRON: an Adaptive Algorithm for Online Control of the False Discovery Rate
- SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation
- Scalable approximate Bayesian inference for particle tracking data
- Scalable Bilinear Pi Learning Using State and Action Features
- Scalable Deletion-Robust Submodular Maximization: Data Summarization with Privacy and Fairness Constraints
- Scalable Gaussian Processes with Grid-Structured Eigenfunctions (GP-GRIEF)
- Selecting Representative Examples for Program Synthesis
- Self-Bounded Prediction Suffix Tree via Approximate String Matching
- Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings
- Self-Imitation Learning
- Semi-Amortized Variational Autoencoders
- Semi-Implicit Variational Inference
- Semiparametric Contextual Bandits
- Semi-Supervised Learning on Data Streams via Temporal Label Propagation
- Semi-Supervised Learning via Compact Latent Space Clustering
- SGD and Hogwild! Convergence Without the Bounded Gradients Assumption
- Shampoo: Preconditioned Stochastic Tensor Optimization
- Signal and Noise Statistics Oblivious Orthogonal Matching Pursuit
- signSGD: Compressed Optimisation for Non-Convex Problems
- SMAC: Simultaneous Mapping and Clustering Using Spectral Decompositions
- Smoothed Action Value Functions for Learning Gaussian Policies
- Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
- Solving Partial Assignment Problems using Random Clique Complexes
- Sound Abstraction and Decomposition of Probabilistic Programs
- SparseMAP: Differentiable Sparse Structured Inference
- Spatio-temporal Bayesian On-line Changepoint Detection with Model Selection
- Spectrally Approximating Large Graphs with Smaller Graphs
- Spline Filters For End-to-End Deep Learning
- Spotlight: Optimizing Device Placement for Training Deep Neural Networks
- Spurious Local Minima are Common in Two-Layer ReLU Neural Networks
- SQL-Rank: A Listwise Approach to Collaborative Ranking
- Stability and Generalization of Learning Algorithms that Converge to Global Optima
- Stabilizing Gradients for Deep Neural Networks via Efficient SVD Parameterization
- Stagewise Safe Bayesian Optimization with Gaussian Processes
- State Abstractions for Lifelong Reinforcement Learning
- State Space Gaussian Processes with Non-Gaussian Likelihood
- Stein Points
- Stein Variational Gradient Descent Without Gradient
- Stein Variational Message Passing for Continuous Graphical Models
- Stochastic PCA with $\ell_2$ and $\ell_1$ Regularization
- Stochastic Proximal Algorithms for AUC Maximization
- Stochastic Training of Graph Convolutional Networks with Variance Reduction
- Stochastic Variance-Reduced Cubic Regularized Newton Method
- Stochastic Variance-Reduced Hamilton Monte Carlo Methods
- Stochastic Variance-Reduced Policy Gradient
- Stochastic Video Generation with a Learned Prior
- Stochastic Wasserstein Barycenters
- StrassenNets: Deep Learning with a Multiplication Budget
- Streaming Principal Component Analysis in Noisy Setting
- Stronger Generalization Bounds for Deep Nets via a Compression Approach
- Structured Control Nets for Deep Reinforcement Learning
- Structured Evolution with Compact Architectures for Scalable Policy Optimization
- Structured Output Learning with Abstention: Application to Accurate Opinion Prediction
- Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors
- Structured Variationally Auto-encoded Optimization
- Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis
- Submodular Hypergraphs: p-Laplacians, Cheeger Inequalities and Spectral Clustering
- Subspace Embedding and Linear Regression with Orlicz Norm
- Synthesizing Programs for Images using Reinforced Adversarial Learning
- Synthesizing Robust Adversarial Examples
- TACO: Learning Task Decomposition via Temporal Alignment for Control
- TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service
- Tempered Adversarial Networks
- Temporal Poisson Square Root Graphical Models
- Tenth International Workshop Modelling and Reasoning in Context (MRC)
- Testing Sparsity over Known and Unknown Bases
- The 2018 Joint Workshop on Machine Learning for Music
- The 3rd International workshop on biomedical informatics with optimization and machine learning (BOOM)
- The 3rd International Workshop on Knowledge Discovery in Healthcare Data
- The AAMAS-IJCAI Workshop on Agents and Incentives in Artificial Intelligence (day 1)
- The AAMAS-IJCAI Workshop on Agents and Incentives in Artificial Intelligence (day 2)
- The Dynamics of Learning: A Random Matrix Approach
- The Edge Density Barrier: Computational-Statistical Tradeoffs in Combinatorial Inference
- The Generalization Error of Dictionary Learning with Moreau Envelopes
- The Hidden Vulnerability of Distributed Learning in Byzantium
- The Hierarchical Adaptive Forgetting Variational Filter
- The Joint International Workshop on Social Influence Analysis and Mining Actionable Insights from Social Networks (SocInf+MAISoN 2018)
- The Limits of Maxing, Ranking, and Preference Learning
- The Mechanics of n-Player Differentiable Games
- The Mirage of Action-Dependent Baselines in Reinforcement Learning
- The Multilinear Structure of ReLU Networks
- Theoretical Analysis of Image-to-Image Translation with Adversarial Learning
- Theoretical Analysis of Sparse Subspace Clustering with Missing Entries
- Theoretical Foundations and Applications of Deep Generative Models (day 1)
- Theoretical Foundations and Applications of Deep Generative Models (day 2)
- Theory of Deep Learning
- The Power of Interpolation: Understanding the Effectiveness of SGD in Modern Over-parametrized Learning
- The Uncertainty Bellman Equation and Exploration
- The Weighted Kendall and High-order Kernels for Permutations
- The Well-Tempered Lasso
- Thompson Sampling for Combinatorial Semi-Bandits
- Tighter Variational Bounds are Not Necessarily Better
- Tight Regret Bounds for Bayesian Optimization in One Dimension
- Time Limits in Reinforcement Learning
- Topological mixture estimation
- To Understand Deep Learning We Need to Understand Kernel Learning
- Towards Binary-Valued Gates for Robust LSTM Training
- Towards Black-box Iterative Machine Teaching
- Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron
- Towards Fast Computation of Certified Robustness for ReLU Networks
- Towards learning with limited labels: Equivariance, Invariance, and Beyond
- Towards More Efficient Stochastic Decentralized Learning: Faster Convergence and Sparse Communication
- Toward Theoretical Understanding of Deep Learning
- Tractable Probabilistic Models
- Trainable Calibration Measures for Neural Networks from Kernel Mean Embeddings
- Training Neural Machines with Trace-Based Supervision
- Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement
- Transfer Learning via Learning to Transfer
- Transformation Autoregressive Networks
- Tree Edit Distance Learning via Adaptive Symbol Embeddings
- Tropical Geometry of Deep Neural Networks
- TRUST Workshop
- Ultra Large-Scale Feature Selection using Count-Sketches
- Unbiased Objective Estimation in Predictive Optimization
- Understanding and Simplifying One-Shot Architecture Search
- Understanding Generalization and Optimization Performance of Deep CNNs
- Understanding the Loss Surface of Neural Networks for Binary Classification
- Understanding your Neighbors: Practical Perspectives From Modern Analysis
- Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control
- Using Inherent Structures to design Lean 2-layer RBMs
- Using Reward Machines for High-Level Task Specification and Decomposition in Reinforcement Learning
- Variable Selection via Penalized Neural Network: a Drop-Out-One Loss Approach
- Variance Regularized Counterfactual Risk Minimization via Variational Divergence Minimization
- Variational Bayes and Beyond: Bayesian Inference for Big Data
- Variational Bayesian dropout: pitfalls and fixes
- Variational Inference and Model Selection with Generalized Evidence Bounds
- Variational Network Inference: Strong and Stable with Concrete Support
- Video Prediction with Appearance and Motion Conditions
- Visualizing and Understanding Atari Agents
- Weakly Consistent Optimal Pricing Algorithms in Repeated Posted-Price Auctions with Strategic Buyer
- Weakly Submodular Maximization Beyond Cardinality Constraints: Does Randomization Help Greedy?
- Weightless: Lossy weight encoding for deep neural network compression
- Which Training Methods for GANs do actually Converge?
- WHInter: A Working set algorithm for High-dimensional sparse second order Interaction models
- Workshop on AI for Internet of Things
- Workshop on Efficient Credit Assignment in Deep Learning and Deep Reinforcement Learning (ECA) (day 1)
- Workshop on Efficient Credit Assignment in Deep Learning and Deep Reinforcement Learning (ECA) (day 2)
- WSNet: Compact and Efficient Networks Through Weight Sampling
- Yes, but Did It Work?: Evaluating Variational Inference