ICML 2017

THE CONFERENCE

FOR AUTHORS

FOR PARTICIPANTS

Search Schedule »

Search:

Session:

Event type:

Hide breaks and receptions:

Day:

Show All »

Timezone: Australia/Sydney »

Indicates the beginning of a session

Time	C4.9& C4.10	Darling Harbour Theatre	C4.8	C4.1	Parkside 2	C4.5	Parkside 1	C4.6 & C4.7	C4.4	Ground Level	Ballroom
Sun Aug 06, 2017
12:00 AM (Breaks)										Registration Desk
09:00 AM (Invited Talks)		Invited Talk - Bernhard Schölkopf Causal Learning
10:30 AM (Talks)	Probabilistic learning 1 Robust Probabilistic Modeling with Bayesian Data Reweighting	Deep learning 1: backprop Decoupled Neural Interfaces using Synthetic Gradients	Deep learning theory 1 The loss surface of deep and wide neural networks	Online learning 1 Multi-objective Bandits: Optimizing the Generalized Gini Index	Continuous optimization 1 Tight Bounds for Approximate Carathéodory and Beyond	Reinforcement learning 1 Robust Adversarial Reinforcement Learning	Deep generative models 1 PixelCNN Models with Auxiliary Variables for Natural Image Modeling	Supervised learning 1 Enumerating Distinct Decision Trees	Latent feature models Communication-efficient Algorithms for Distributed Stochastic Principal Component Analysis
10:48 AM (Talks)	Post-Inference Prior Swapping	Understanding Synthetic Gradients and Decoupled Neural Interfaces	Neural Taylor Approximations: Convergence and Exploration in Rectifier Networks	Online Learning with Local Permutations and Delayed Feedback	Oracle Complexity of Second-Order Methods for Finite-Sum Problems	Minimax Regret Bounds for Reinforcement Learning	Parallel Multiscale Autoregressive Density Estimation	Simultaneous Learning of Trees and Representations for Extreme Classification and Density Estimation	SPLICE: Fully Tractable Hierarchical Extension of ICA with Pooling
11:06 AM (Talks)	Evaluating Bayesian Models with Posterior Dispersion Indices	meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting	Sharp Minima Can Generalize For Deep Nets	Model-Independent Online Learning for Influence Maximization	Global optimization of Lipschitz functions	Fairness in Reinforcement Learning	Video Pixel Networks	Resource-efficient Machine Learning in 2 KB RAM for the Internet of Things	Latent Feature Lasso
11:15 AM (Breaks)											Opening Reception
11:24 AM (Talks)	Automatic Discovery of the Statistical Types of Variables in a Dataset	Learning Important Features Through Propagating Activation Differences	Geometry of Neural Network Loss Surfaces via Random Matrix Theory	Online Learning to Rank in Stochastic Click Models	Strong NP-Hardness for Sparse Optimization with Concave Penalty Functions	Boosted Fitted Q-Iteration	Adversarial Variational Bayes: Unifying Variational Autoencoders and Generative Adversarial Networks	Multi-Class Optimal Margin Distribution Machine	Online Partial Least Square Optimization: Dropping Convexity for Better Efficiency and Scalability
11:42 AM (Talks)	Bayesian Models of Data Streams with Hierarchical Power Priors	Evaluating the Variance of Likelihood-Ratio Gradient Estimators	The Shattered Gradients Problem: If resnets are the answer, then what is the question?	The Sample Complexity of Online One-Class Collaborative Filtering	Stochastic Convex Optimization: Faster Local Growth Implies Faster Global Convergence	Why is Posterior Sampling Better than Optimism for Reinforcement Learning?	Learning Texture Manifolds with the Periodic Spatial GAN	Kernelized Support Tensor Machines
01:30 PM (Talks)	Probabilistic learning 2 Ordinal Graphical Models: A Tale of Two Approaches	Deep learning 2: invariances Equivariance Through Parameter-Sharing	Deep learning theory 2 Recovery Guarantees for One-hidden-layer Neural Networks	Online learning 2 Efficient Regret Minimization in Non-Convex Games	Continuous optimization 2 GSOS: Gauss-Seidel Operator Splitting Algorithm for Multi-Term Nonsmooth Convex Composite Optimization	Reinforcement learning 2 Constrained Policy Optimization	Deep generative models 2 Generalization and Equilibrium in Generative Adversarial Nets (GANs)	Supervised learning 2 Dual Supervised Learning	Matrix factorization 1 Coresets for Vector Summarization with Applications to Network Graphs
01:48 PM (Talks)	Scalable Bayesian Rule Lists	Warped Convolutions: Efficient Invariance to Spatial Transformations	Failures of Gradient-Based Deep Learning	Identify the Nash Equilibrium in Static Games with Random Payoffs	Breaking Locality Accelerates Block Gauss-Seidel	Reinforcement Learning with Deep Energy-Based Policies	McGan: Mean and Covariance Feature Matching GAN	Learning Infinite Layer Networks without the Kernel Trick	Partitioned Tensor Factorizations for Learning Mixed Membership Models
02:06 PM (Talks)	Learning Determinantal Point Processes with Moments and Cycles	Graph-based Isometry Invariant Representation Learning	Analytical Guarantees on Numerical Precision of Deep Neural Networks	Follow the Compressed Leader: Faster Online Learning of Eigenvectors and Faster MMWU	Stochastic DCA for the Large-sum of Non-convex Functions Problem and its Application to Group Variable Selection in Classification	Prediction and Control with Temporal Segment Models	Conditional Image Synthesis with Auxiliary Classifier GANs	Random Fourier Features for Kernel Ridge Regression: Approximation Bounds and Statistical Guarantees	On Mixed Memberships and Symmetric Nonnegative Matrix Factorizations
02:24 PM (Talks)	Deep Bayesian Active Learning with Image Data	Deriving Neural Architectures from Sequence and Graph Kernels	Follow the Moving Leader in Deep Learning	On Kernelized Multi-armed Bandits	Gradient Projection Iterative Sketch for Large-Scale Constrained Least-Squares	An Alternative Softmax Operator for Reinforcement Learning	Learning to Discover Cross-Domain Relations with Generative Adversarial Networks	Logarithmic Time One-Against-Some	Nonnegative Matrix Factorization for Time Series Recovery From a Few Temporal Aggregates
02:42 PM (Talks)	Bayesian Boolean Matrix Factorisation	Unsupervised Learning by Predicting Noise	Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank	Second-Order Kernel Online Convex Optimization with Adaptive Sketching	Connected Subgraph Detection with Mirror Descent on SDPs	Fake News Mitigation via Point Process Based Intervention	Wasserstein Generative Adversarial Networks	Understanding Black-box Predictions via Influence Functions	Frame-based Data Factorizations
03:30 PM (Talks)	Probabilistic learning 3 Learning the Structure of Generative Models without Labeled Data	Deep learning 3: metalearning Deep Transfer Learning with Joint Adaptation Networks	Deep learning theory 3 Globally Optimal Gradient Descent for a ConvNet with Gaussian Inputs	Online learning 3 Dueling Bandits with Weak Regret	Continuous optimization 3 Prox-PDA: The Proximal Primal-Dual Algorithm for Fast Distributed Nonconvex Optimization and Learning Over Networks	Reinforcement learning 3 Curiosity-driven Exploration by Self-supervised Prediction	Deep generative models 3 Learning Hierarchical Features from Deep Generative Models	Semisupervised and curriculum learning Re-revisiting Learning on Hypergraphs: Confidence Interval and Subgradient Method	Matrix factorization 2 Nearly Optimal Robust Matrix Completion
03:48 PM (Talks)	Learning to Discover Sparse Graphical Models	Meta Networks	Convexified Convolutional Neural Networks	On Context-Dependent Clustering of Bandits	Exploiting Strong Convexity from Data with Primal-Dual First-Order Algorithms	Interactive Learning from Policy-Dependent Human Feedback	Bottleneck Conditional Density Estimation	Self-Paced Co-training	Provable Alternating Gradient Descent for Non-negative Matrix Factorization with Strong Correlations
04:06 PM (Talks)	Local-to-Global Bayesian Network Structure Learning	SplitNet: Learning to Semantically Split Deep Networks for Parameter Reduction and Model Parallelization	On the Expressive Power of Deep Neural Networks	Provably Optimal Algorithms for Generalized Linear Contextual Bandits	Doubly Greedy Primal-Dual Coordinate Descent for Sparse Empirical Risk Minimization	End-to-End Differentiable Adversarial Imitation Learning	Learning Deep Latent Gaussian Models with Markov Chain Monte Carlo	Semi-Supervised Classification Based on Classification from Positive and Unlabeled Data	No Spurious Local Minima in Nonconvex Low Rank Problems: A Unified Geometric Analysis
04:24 PM (Talks)	Composing Tree Graphical Models with Persistent Homology Features for Clustering Mixed-Type Data	Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks	Depth-Width Tradeoffs in Approximating Natural Functions With Neural Networks	Safety-Aware Algorithms for Adversarial Contextual Bandit	A Richer Theory of Convex Constrained Optimization with Reduced Projections and Improved Rates	Learning in POMDPs with Monte Carlo Tree Search	Zero-Inflated Exponential Family Embeddings	Iterative Machine Teaching	Coherence Pursuit: Fast, Simple, and Robust Subspace Recovery
04:42 PM (Talks)	On Relaxing Determinism in Arithmetic Circuits	AdaNet: Adaptive Structural Learning of Artificial Neural Networks		Adaptive Multiple-Arm Identification	Convex Phase Retrieval without Lifting via PhaseMax	DARLA: Improving Zero-Shot Transfer in Reinforcement Learning		Automated Curriculum Learning for Neural Networks	Tensor Decomposition with Smoothness

Time	Gallery	C4.9& C4.10	Darling Harbour Theatre	C4.8	C4.1	Parkside 2	C4.5	Parkside 1	C4.6 & C4.7	C4.4	Ground Level	The Press Room at the ICC
Mon Aug 07, 2017
05:15 PM (Talks)		Bayesian Nonparametrics An Infinite Hidden Markov Model With Similarity-Biased Transitions	Deep learning 4: learning to learn Learning to Learn without Gradient Descent by Gradient Descent	Active learning Efficient Nonmyopic Active Search	Online learning 4 Efficient Online Bandit Multiclass Learning with O(sqrt{T}) Regret	Continuous optimization 4 A Semismooth Newton Method for Fast, Generic Convex Programming	Reinforcement learning 4 Unifying task specification in reinforcement learning	Recurrent neural networks 1 Attentive Recurrent Comparators	Transfer and multitask learning Asymmetric Tri-training for Unsupervised Domain Adaptation	Matrix factorization 3 Orthogonalized ALS: A Theoretically Principled Tensor Decomposition Algorithm for Practical Use
05:33 PM (Talks)		Batched High-dimensional Bayesian Optimization via Structural Kernel Learning	Learned Optimizers that Scale and Generalize	Leveraging Union of Subspace Structure to Improve Constrained Clustering	Active Learning for Accurate Estimation of Linear Models	Approximate Newton Methods and Their Local Convergence	A Distributional Perspective on Reinforcement Learning	State-Frequency Memory Recurrent Neural Networks	Source-Target Similarity Modelings for Multi-Source Transfer Gaussian Process Regression	Tensor Decomposition via Simultaneous Power Iteration
05:51 PM (Talks)		From Patches to Images: A Nonparametric Generative Model	Learning Gradient Descent: Better Generalization and Longer Horizons	Active Heteroscedastic Regression	Adaptive Feature Selection: Computationally Efficient Online Sparse Linear Regression under RIP	Stochastic Adaptive Quasi-Newton Methods for Minimizing Expected Values	Hierarchy Through Composition with Multitask LMDPs	Delta Networks for Optimized Recurrent Network Computation	Multi-task Learning with Labeled and Unlabeled Tasks	A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery
06:09 PM (Talks)		Fast Bayesian Intensity Estimation for the Permanental Process	Learning Algorithms for Active Learning	Active Learning for Cost-Sensitive Classification	Emulating the Expert: Inverse Optimization through Online Learning	Practical Gauss-Newton Optimisation for Deep Learning	A Laplacian Framework for Option Discovery in Reinforcement Learning	Recurrent Highway Networks	Schema Networks: Zero-shot Transfer with a Generative Causal Model of Intuitive Physics	An Efficient, Sparsity-Preserving, Online Algorithm for Low-Rank Approximation
06:27 PM (Talks)		A Birth-Death Process for Feature Allocation		Diameter-Based Active Learning	Variants of RMSProp and Adagrad with Logarithmic Regret Bounds	Tensor Balancing on Statistical Manifold	Modular Multitask Reinforcement Learning with Policy Sketches		Risk Bounds for Transferring Representations With and Without Fine-Tuning	Algorithms for $\ell_p$ Low-Rank Approximation
06:30 PM (Posters)	Posters Mon
12:00 AM (Breaks)											Registration Desk
01:45 AM (Breaks)			Opening Remarks
03:00 AM (Breaks)												Press Conference
09:00 AM (Talks)			Test of Time Award Test of Time Award
10:30 AM (Talks)		Probabilistic inference 1 Exact MAP Inference by Avoiding Fractional Vertices	Deep learning 5: Fisher approximations Relative Fisher Information and Natural Gradient for Learning Large Modular Models	Learning theory 1 Sketched Ridge Regression: Optimization Perspective, Statistical Perspective, and Model Averaging	Networks and relational learning Leveraging Node Attributes for Incomplete Relational Data	Continuous optimization 5 Lazifying Conditional Gradient Algorithms	Reinforcement learning 5 Data-Efficient Policy Evaluation Through Behavior Policy Search	Recurrent neural networks 2 Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections	Clustering 1 Distributed and Provably Good Seedings for k-Means in Constant Rounds	Spectral methods How Close Are the Eigenvectors of the Sample and Actual Covariance Matrices?
10:48 AM (Talks)		Exact Inference for Integer Latent-Variable Models	Learning Deep Architectures via Generalized Whitened Neural Networks	Estimating the unseen from multiple populations	Bayesian inference on random simple graphs with power law degree distributions	Conditional Accelerated Lazy Stochastic Gradient Descent	Stochastic Variance Reduction Methods for Policy Evaluation	On orthogonality and learning RNNs with long term dependencies	Consistent k-Clustering	Faster Principal Component Regression and Stable Matrix Chebyshev Approximation
11:06 AM (Talks)		Improving Viterbi is Hard: Better Runtimes Imply Faster Clique Algorithms	Continual Learning Through Synaptic Intelligence	Meritocratic Fairness for Cross-Population Selection	Analogical Inference for Multi-relational Embeddings	SARAH: A Novel Method for Machine Learning Problems Using Stochastic Recursive Gradient	Optimal and Adaptive Off-policy Evaluation in Contextual Bandits	Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNNs	Towards K-means-friendly Spaces: Simultaneous Deep Learning and Clustering	Spectral Learning from a Single Trajectory under Finite-State Policies
11:24 AM (Talks)		Variational Inference for Sparse and Undirected Models	Adaptive Neural Networks for Efficient Inference	Neural networks and rational functions	Know-Evolve: Deep Temporal Reasoning for Dynamic Knowledge Graphs	Approximate Steepest Coordinate Descent	Consistent On-Line Off-Policy Evaluation	The Statistical Recurrent Unit	Hyperplane Clustering Via Dual Principal Component Pursuit	Capacity Releasing Diffusion for Speed and Locality.
11:42 AM (Talks)		Tensor Belief Propagation	Combined Group and Exclusive Sparsity for Deep Neural Networks		Deep Generative Models for Relational Data with Side Information	StingyCD: Safely Avoiding Wasteful Updates in Coordinate Descent	Contextual Decision Processes with low Bellman rank are PAC-Learnable	Input Switched Affine Networks: An RNN Architecture Designed for Interpretability	Multilevel Clustering via Wasserstein Means	Doubly Accelerated Methods for Faster CCA and Generalized Eigendecomposition
11:45 AM (Breaks)	Light snack
01:30 PM (Talks)		Probabilistic inference 2 Faster Greedy MAP Inference for Determinantal Point Processes	Deep learning 6 Input Convex Neural Networks	Learning theory 2 Uniform Deviation Bounds for k-Means Clustering	Ranking and preferences ChoiceRank: Identifying Preferences from Node Traffic in Networks	Continuous optimization 6 Stochastic modified equations and adaptive stochastic gradient algorithms	Ensemble methods A Simple Multi-Class Boosting Framework with Theoretical Guarantees and Empirical Proficiency	Recurrent neural networks 3 Online and Linear-Time Attention by Enforcing Monotonic Alignments	Clustering 2 Co-clustering through Optimal Transport	Sparsity 1 On the Iteration Complexity of Support Recovery via Hard Thresholding Pursuit
01:48 PM (Talks)		Zonotope hit-and-run for efficient sampling from projection DPPs	OptNet: Differentiable Optimization as a Layer in Neural Networks	Uniform Convergence Rates for Kernel Density Estimation	Statistical Inference for Incomplete Ranking Data: The Case of Rank-Dependent Coarsening	Dissipativity Theory for Nesterov's Accelerated Method	Gradient Boosted Decision Trees for High Dimensional Sparse Output	Sequence Tutor: Conservative fine-tuning of sequence generation models with KL-control	Multiple Clustering Views from Multiple Uncertain Experts	Dual Iterative Hard Thresholding: From Non-convex Sparse Minimization to Non-smooth Concave Maximization
02:06 PM (Talks)		A Divergence Bound for Hybrids of MCMC and Variational Inference and an Application to Langevin Dynamics and SGVI	Parseval Networks: Improving Robustness to Adversarial Examples	Density Level Set Estimation on Manifolds with DBSCAN	Just Sort It! A Simple and Effective Approach to Active Preference Learning	An Analytical Formula of Population Gradient for two-layered ReLU network and its Applications in Convergence and Critical Point Analysis	Globally Induced Forest: A Prepruning Compression Scheme	Deep Voice: Real-time Neural Text-to-Speech	Clustering by Sum of Norms: Stochastic Incremental Algorithm, Convergence and Cluster Recovery	On The Projection Operator to A Three-view Cardinality Constrained Set
02:24 PM (Talks)		On the Sampling Problem for Kernel Quadrature	Regularising Non-linear Models Using Feature Side-information	Algorithmic Stability and Hypothesis Complexity	Maximum Selection and Ranking under Noisy Comparisons	Forward and Reverse Gradient-Based Hyperparameter Optimization	Forest-type Regression with General Losses and Robust Forest	DeepBach: a Steerable Model for Bach Chorales Generation	Clustering High Dimensional Dynamic Data Streams	Sparse + Group-Sparse Dirty Models: Statistical Guarantees without Unreasonable Conditions and a Case for Non-Convexity
02:42 PM (Talks)		Measuring Sample Quality with Kernels		Consistency Analysis for Binary Classification Revisited	Active Learning for Top-$K$ Rank Aggregation from Noisy Comparisons	Adaptive Sampling Probabilities for Non-Smooth Optimization	Confident Multiple Choice Learning	Neural Audio Synthesis of Musical Notes with WaveNet Autoencoders		Compressed Sensing using Generative Models
03:30 PM (Talks)		Probabilistic inference 3 Variational Boosting: Iteratively Refining Posterior Approximations	Deep learning 7: analysis A Closer Look at Memorization in Deep Networks	Infomation theory Distributed Mean Estimation with Limited Communication	ML and programming Learning to Align the Source Code to the Compiled Object Code	Continuous optimization 7 Sub-sampled Cubic Regularization for Non-convex Optimization	Game theory and multiagents Regret Minimization in Behaviorally-Constrained Zero-Sum Games	Recurrent neural networks 4 Learning to Generate Long-term Future via Hierarchical Prediction	Metric learning Fast k-Nearest Neighbour Search via Prioritized DCI	Sparsity 2 Scaling Up Sparse Support Vector Machines by Simultaneous Feature and Sample Reduction
03:48 PM (Talks)		Lost Relatives of the Gumbel Trick	Cognitive Psychology for Deep Neural Networks: A Shape Bias Case Study	Nonparanormal Information Estimation	RobustFill: Neural Program Learning under Noisy I/O	Natasha: Faster Non-Convex Stochastic Optimization Via Strongly Non-Convex Parameter	Reduced Space and Faster Convergence in Imperfect-Information Games via Pruning	Sequence to Better Sequence: Continuous Revision of Combinatorial Structures	Deep Spectral Clustering Learning	Efficient Distributed Learning with Sparsity
04:06 PM (Talks)		Learning to Aggregate Ordinal Labels by Maximizing Separating Width	Visualizing and Understanding Multilayer Perceptron Models: A Case Study in Speech Processing	A Unified Maximum Likelihood Approach for Estimating Symmetric Properties of Discrete Distributions	Programming with a Differentiable Forth Interpreter	“Convex Until Proven Guilty”: Dimension-Free Acceleration of Gradient Descent on Non-Convex Functions	Strongly-Typed Agents are Guaranteed to Interact Safely	Tensor-Train Recurrent Neural Networks for Video Classification	Joint Dimensionality Reduction and Metric Learning: A Geometric Take	Innovation Pursuit: A New Approach to the Subspace Clustering Problem
04:24 PM (Talks)		Uncorrelation and Evenness: a New Diversity-Promoting Regularizer	Axiomatic Attribution for Deep Networks	Gradient Coding: Avoiding Stragglers in Distributed Learning	Differentiable Programs with Neural Libraries	Convergence Analysis of Proximal Gradient with Momentum for Nonconvex Optimization	Coordinated Multi-Agent Imitation Learning	Sequence Modeling via Segmentations	ProtoNN: Compressed and Accurate kNN for Resource-scarce Devices	Selective Inference for Sparse High-Order Interaction Models
04:42 PM (Talks)		Learning Latent Space Models with Angular Constraints	On Calibration of Modern Neural Networks	Learning Discrete Representations via Information Maximizing Self-Augmented Training	Developing Bug-Free Machine Learning Systems With Formal Mathematics	How to Escape Saddle Points Efficiently	Deep Decentralized Multi-task Multi-Agent Reinforcement Learning under Partial Observability	Latent LSTM Allocation: Joint clustering and non-linear dynamic modeling of sequence data		Dictionary Learning Based on Sparse Distribution Tomography

Time	Gallery	C4.9& C4.10	Darling Harbour Theatre	C4.8	C4.1	Parkside 2	C4.5	Parkside 1	C4.6 & C4.7	C4.4	Ground Level
Tue Aug 08, 2017
05:15 PM (Invited Talks)			Invited Talk - Peter Donnelly Genomics, Big Data, and Machine Learning: Understanding the Human Wiring Diagram and Driving the Healthcare Revolution
06:30 PM (Posters)	Posters Tue
12:00 AM (Breaks)											Registration Desk
09:00 AM (Invited Talks)			Invited Talk - Raia Hadsell Towards Reinforcement Learning in the Real World
10:30 AM (Talks)		Monte Carlo methods 1 Fractional Langevin Monte Carlo: Exploring Levy Driven Stochastic Differential Equations for MCMC	Deep learning 8: hardware Device Placement Optimization with Reinforcement Learning	Privacy and security 1 Differentially Private Ordinary Least Squares	Bayesian Optimization Preferential Bayesian Optmization	Distributed optimization Asynchronous Stochastic Gradient Descent with Delay Compensation	Continuous control Improving Stochastic Policy Gradients in Continuous Control with Deep Reinforcement Learning using the Beta Distribution	Language 1 Dynamic Word Embeddings	Healthcare When can Multi-Site Datasets be Pooled for Regression? Hypothesis Tests, $\ell_2$-consistency and Neuroscience Applications	High dimensional estimation Being Robust (in High Dimensions) Can Be Practical
10:48 AM (Talks)		Stochastic Bouncy Particle Sampler	Deep Tensor Convolution on Multicores	Priv’IT: Private and Sample Efficient Identity Testing	Max-value Entropy Search for Efficient Bayesian Optimization	Adaptive Consensus ADMM for Distributed Optimization	Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning	Gram-CTC: Automatic Unit Selection and Target Decomposition for Sequence Labelling	Learning from Clinical Judgments: Semi-Markov-Modulated Marked Hawkes Processes for Risk Prognosis	Multilabel Classification with Group Testing and Codes
11:06 AM (Talks)		Canopy --- Fast Sampling with Cover Trees	MEC: Memory-efficient Convolution for Deep Neural Network	Differentially Private Submodular Maximization: Data Summarization in Disguise	Bayesian Optimization with Tree-structured Dependencies	Optimal Algorithms for Smooth and Strongly Convex Distributed Optimization in Networks	Prediction under Uncertainty in Sparse Spectrum Gaussian Processes with Applications to Filtering and Control	Coupling Distributed and Symbolic Execution for Natural Language Queries	Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier	High-Dimensional Structured Quantile Regression
11:15 AM (Breaks)	Light snack
11:24 AM (Talks)		A Simulated Annealing Based Inexact Oracle for Wasserstein Loss Minimization	Beyond Filters: Compact Feature Map for Portable Deep Model	Differentially Private Learning of Graphical Models using CGMs	Multi-fidelity Bayesian Optimisation with Continuous Approximations	Projection-free Distributed Online Learning in Networks	Learning Stable Stochastic Nonlinear Dynamical Systems	Image-to-Markup Generation with Coarse-to-Fine Attention	iSurvive: An Interpretable, Event-time Prediction Model for mHealth	High-dimensional Non-Gaussian Single Index Models via Thresholded Score Function Estimation
11:42 AM (Talks)		Improving Gibbs Sampler Scan Quality with DoGS	Efficient softmax approximation for GPUs	Minimizing Trust Leaks for Robust Sybil Detection	Parallel and Distributed Thompson Sampling for Large-scale Accelerated Exploration of Chemical Space		Local Bayesian Optimization of Motor Skills	Multichannel End-to-end Speech Recognition	Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture	Robust Structured Estimation with Single-Index Models
01:30 PM (Talks)		Monte Carlo methods 2 Magnetic Hamiltonian Monte Carlo	Deep learning 9: probabilistic Dropout Inference in Bayesian Neural Networks with Alpha-divergences	Privacy and security 2 The Price of Differential Privacy For Online Learning	Causal Inference 1 Uncertainty Assessment and False Discovery Rate Control in High-Dimensional Granger Causal Inference	Combinatorial optimization 1 Robust Guarantees of Stochastic Greedy Algorithms	Deep reinforcement learning 1 Count-Based Exploration with Neural Density Models	Language 2 Latent Intention Dialogue Models	Time series Bidirectional learning for time-series models with hidden units	Robust Estimation Toward Efficient and Accurate Covariance Matrix Estimation on Compressed Data
01:48 PM (Talks)		Probabilistic Path Hamiltonian Monte Carlo	Multiplicative Normalizing Flows for Variational Bayesian Neural Networks	Pain-Free Random Differential Privacy with Sensitivity Sampling	Uncovering Causality from Multivariate Hawkes Integrated Cumulants	Guarantees for Greedy Maximization of Non-submodular Functions with Applications	Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning	Discovering Discrete Latent Topics with Neural Variational Inference	Learning Hawkes Processes from Short Doubly-Censored Event Sequences	Robust Gaussian Graphical Model Estimation with Arbitrary Corruption
02:06 PM (Talks)		Stochastic Gradient Monomial Gamma Sampler	Variational Dropout Sparsifies Deep Neural Networks	Differentially Private Clustering in High-Dimensional Euclidean Spaces	Cost-Optimal Learning of Causal Graphs	Robust Submodular Maximization: A Non-Uniform Partitioning Approach	Stabilising Experience Replay for Deep Multi-Agent Reinforcement Learning	Toward Controlled Generation of Text	Coherent probabilistic forecasts for hierarchical time series	Algebraic Variety Models for High-Rank Matrix Completion
02:24 PM (Talks)		Stochastic Gradient MCMC Methods for Hidden Markov Models	Unimodal Probability Distributions for Deep Ordinal Classification	Differentially Private Chi-squared Test by Unit Circle Mechanism	Identification and Model Testing in Linear Structural Equation Models using Auxiliary Variables	Probabilistic Submodular Maximization in Sub-Linear Time	The Predictron: End-To-End Learning and Planning	Learning Continuous Semantic Representations of Symbolic Expressions	Soft-DTW: a Differentiable Loss Function for Time-Series	High-Dimensional Variance-Reduced Stochastic Gradient Expectation-Maximization Algorithm
02:42 PM (Talks)		Deep Latent Dirichlet Allocation with Topic-Layer-Adaptive Stochastic Gradient Riemannian MCMC		Collect at Once, Use Effectively: Making Non-interactive Locally Private Learning Possible	Estimating individual treatment effect: generalization bounds and algorithms	On Approximation Guarantees for Greedy Low Rank Optimization	Averaged-DQN: Variance Reduction and Stabilization for Deep Reinforcement Learning	Adversarial Feature Matching for Text Generation	Variational Policy for Guiding Point Processes
03:30 PM (Talks)		Gaussian processes Distributed Batch Gaussian Process Optimization	Applications Dance Dance Convolution	Kernel methods An Adaptive Test of Independence with Analytic Kernel Embeddings	Causal Inference 2 Recursive Partitioning for Personalization using Observational Data	Combinatorial optimization 2 Deletion-Robust Submodular Maximization: Data Summarization with "the Right to be Forgotten"	Deep reinforcement learning 2 FeUdal Networks for Hierarchical Reinforcement Learning	Language 3 Language Modeling with Gated Convolutional Networks	Structured prediction Deep Value Networks Learn to Evaluate and Iteratively Refine Structured Outputs	Large scale learning Optimal Densification for Fast and Accurate Minwise Hashing
03:48 PM (Talks)		Scalable Multi-Class Gaussian Process Classification using Expectation Propagation	World of Bits: An Open-Domain Platform for Web-Based Agents	Sliced Wasserstein Kernel for Persistence Diagrams	Identifying Best Interventions through Online Importance Sampling	Analysis and Optimization of Graph Decompositions by Lifted Multicuts	Deciding How to Decide: Dynamic Routing in Artificial Neural Networks	Convolutional Sequence to Sequence Learning	Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction	Stochastic Generative Hashing
04:06 PM (Talks)		Random Feature Expansions for Deep Gaussian Processes	Real-Time Adaptive Image Compression	Adapting Kernel Representations Online Using Submodular Maximization	Deep IV: A Flexible Approach for Counterfactual Prediction	Near-Optimal Design of Experiments via Regret Minimization	Neural Episodic Control	Improved Variational Autoencoders for Text Modeling using Dilated Convolutions	End-to-End Learning for Structured Prediction Energy Networks	ZipML: Training Linear Models with End-to-End Low Precision, and a Little Bit of Deep Learning
04:24 PM (Talks)		Asynchronous Distributed Variational Gaussian Processes for Regression	Neural Message Passing for Quantum Chemistry	Spherical Structured Feature Maps for Kernel Approximation	Counterfactual Data-Fusion for Online Reinforcement Learners	Robust Budget Allocation via Continuous Submodular Functions	Neural Optimizer Search using Reinforcement Learning	Grammar Variational Autoencoder	A Unified View of Multi-Label Performance Measures	Large-Scale Evolution of Image Classifiers
04:42 PM (Talks)		High Dimensional Bayesian Optimization with Elastic Gaussian Process	Accelerating Eulerian Fluid Simulation With Convolutional Networks	Nyström Method with Kernel K-means++ Samples as Landmarks		Rule-Enhanced Penalized Regression by Column Generation using Rectangular Maximum Agreement			Scalable Generative Models for Multi-label Learning with Missing Labels

Time	Gallery	Darling Harbour Theatre	C4.8	C4.1	C4.5	Parkside 1	C4.4	Ground Level	C4.10	C4.3	C4.7	C4.6	C4.9	C4.11	Ballroom
Wed Aug 09, 2017
05:15 PM (Invited Talks)		Invited Talk - Latanya Sweeney How AI Designers will Dictate Our Civic Future
06:30 PM (Posters)	Posters Wed
12:00 AM (Breaks)								Registration Desk
05:00 AM (Breaks)						Open Business Meeting
08:30 AM (Workshops)			Workshop on Human Interpretability in Machine Learning (WHI)	Lifelong Learning: A Reinforcement Learning Approach	Principled Approaches to Deep Learning	Implicit Generative Models	Workshop on Computational Biology		ICML Workshop on Machine Learning for Autonomous Vehicles 2017	Workshop on Visualization for Deep Learning	ML on a budget: IoT, Mobile and other tiny-ML applications	Video Games and Machine Learning	Automatic Machine Learning (AutoML 2017)	Learning to Generate Natural Language
11:15 AM (Breaks)															Closing Reception

Time	C4.8	C4.1	Parkside 1	C4.4	Ground Level	C4.10	C4.3	C4.7	C4.6	C4.9	C4.11
Thu Aug 10, 2017
12:00 AM (Breaks)					Registration Desk
08:30 AM (Workshops)	Human in the Loop Machine Learning	Time Series Workshop	Reinforcement Learning Workshop	Private and Secure Machine Learning		Reproducibility in Machine Learning Research	Machine Learning in Speech and Language Processing	Reliable Machine Learning in the Wild	Picky Learners: Choosing Alternative Ways to Process Data.	Machine Learning for Music Discovery	Interactive Machine Learning and Semantic Information Retrieval

Time	C4.5	Ground Level
Fri Aug 11, 2017
12:00 AM (Breaks)		Registration Desk
01:30 AM (Workshops)	Deep Structured Prediction

Time
Sat Aug 12, 2017

Sun Aug 06, 2017

Mon Aug 07, 2017

Tue Aug 08, 2017

Wed Aug 09, 2017

Thu Aug 10, 2017

Fri Aug 11, 2017

Sat Aug 12, 2017