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

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

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

Time	Gallery	C4.5	C4.1	C4.4	Parkside 1	C4.8	Ground Level	Ballroom	Darling Harbour Theatre	C4.7	C4.9	C4.10	C4.6	C4.3	C4.11
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)		Principled Approaches to Deep Learning	Lifelong Learning: A Reinforcement Learning Approach	Workshop on Computational Biology	Implicit Generative Models	Workshop on Human Interpretability in Machine Learning (WHI)				ML on a budget: IoT, Mobile and other tiny-ML applications	Automatic Machine Learning (AutoML 2017)	ICML Workshop on Machine Learning for Autonomous Vehicles 2017	Video Games and Machine Learning	Workshop on Visualization for Deep Learning	Learning to Generate Natural Language
11:15 AM (Breaks)								Closing Reception

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

Time
Fri Aug 11, 2017
12:00 AM (Breaks)
01:30 AM (Workshops)

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