Search Schedule »

Show All »

Timezone: America/Montreal »

Indicates the beginning of a session

 Mon Dec 07, 2015

Time Level 2 room 210 AB 210 C #20 210 C #18 210 C #24 210 C #98 210 C #81 210 C #34 210 C #71 210 C #46 210 C #85 210 C #54 210 C #3 210 C #94 210 C #83 210 C #51 210 C #62 210 C #58 210 C #8 210 C #21 210 C #10 210 C #97 210 C #95 210 C #13 210 C #61 210 C #15 210 C #11 210 C #100 210 C #68 210 C #66 210 C #76 210 C #57 210 C #48 210 C #14 210 C #52 210 C #28 210 C #26 210 C #40 210 C #43 210 C #42 210 C #4 210 C #37 210 C #45 210 C #80 210 C #82 210 C #6 210 C #49 210 C #30 210 C #87 210 C #1 210 C #78 210 C #96 210 C #12 210 C #102 210 C #70 210 C #22 210 C #39 210 C #101 210 C #89 210 C #77 210 C #75 210 C #84 210 C #67 210 C #25 210 C #19 210 C #32 210 C #2 210 C #7 210 C #29 210 C #72 210 C #59 210 C #60 210 C #38 210 C #33 210 C #63 210 C #90 210 C #50 210 C #88 210 C #92 210 C #56 210 C #35 210 C #99 210 C #55 210 C #16 210 C #5 210 C #73 210 C #41 210 C #53 210 C #69 210 C #47 210 C #91 210 C #65 210 C #36 210 C #74 210 C #44 210 C #79 210 C #64 210 C #9 210 C #31 210 C #27 210 C #17 210 C #93 210 C #23 Level 2 room 210 E,F 220 A
09:30 AM (Tutorials)
Deep Learning
Large-Scale Distributed Systems for Training Neural Networks
11:00 AM (Breaks)
Breakfast
01:00 PM (Tutorials)
Monte Carlo Inference Methods
Probabilistic Programming
03:30 PM (Tutorials)
Introduction to Reinforcement Learning with Function Approximation
High-Performance Hardware for Machine Learning
07:00 PM (Posters)
Recognizing retinal ganglion cells in the dark 210 C #20
A Theory of Decision Making Under Dynamic Context 210 C #18
Hidden Technical Debt in Machine Learning Systems 210 C #24
Minimax Time Series Prediction 210 C #98
Differentially Private Learning of Structured Discrete Distributions 210 C #81
Variational Dropout and the Local Reparameterization Trick 210 C #34
Robust Gaussian Graphical Modeling with the Trimmed Graphical Lasso 210 C #71
Local Expectation Gradients for Black Box Variational Inference 210 C #46
Taming the Wild: A Unified Analysis of Hogwild-Style Algorithms 210 C #85
Adversarial Prediction Games for Multivariate Losses 210 C #54
Grammar as a Foreign Language 210 C #3
Regularization-Free Estimation in Trace Regression with Symmetric Positive Semidefinite Matrices 210 C #94
Bayesian Optimization with Exponential Convergence 210 C #83
Learning with Relaxed Supervision 210 C #51
Basis refinement strategies for linear value function approximation in MDPs 210 C #62
Online Prediction at the Limit of Zero Temperature 210 C #58
Exploring Models and Data for Image Question Answering 210 C #8
A Recurrent Latent Variable Model for Sequential Data 210 C #21
Parallel Multi-Dimensional LSTM, With Application to Fast Biomedical Volumetric Image Segmentation 210 C #10
Nearly Optimal Private LASSO 210 C #97
Convergence Analysis of Prediction Markets via Randomized Subspace Descent 210 C #95
The Poisson Gamma Belief Network 210 C #13
Sample Complexity Bounds for Iterative Stochastic Policy Optimization 210 C #61
BinaryConnect: Training Deep Neural Networks with binary weights during propagations 210 C #15
Learning From Small Samples: An Analysis of Simple Decision Heuristics 210 C #11
Explore no more: Improved high-probability regret bounds for non-stochastic bandits 210 C #100
Poster Session
Decomposition Bounds for Marginal MAP 210 C #68
Discrete Rényi Classifiers 210 C #66
A class of network models recoverable by spectral clustering 210 C #76
Rate-Agnostic (Causal) Structure Learning 210 C #57
Principal Geodesic Analysis for Probability Measures under the Optimal Transport Metric 210 C #48
Semi-Supervised Factored Logistic Regression for High-Dimensional Neuroimaging Data 210 C #14
M-Statistic for Kernel Change-Point Detection 210 C #52
Dependent Multinomial Models Made Easy: Stick-Breaking with the Polya-gamma Augmentation 210 C #28
Calibrated Structured Prediction 210 C #26
Model-Based Relative Entropy Stochastic Search 210 C #40
Embedding Inference for Structured Multilabel Prediction 210 C #43
Expectation Particle Belief Propagation 210 C #42
Recursive Training of 2D-3D Convolutional Networks for Neuronal Boundary Prediction 210 C #4
Copula variational inference 210 C #37
Double or Nothing: Multiplicative Incentive Mechanisms for Crowdsourcing 210 C #45
Spectral Norm Regularization of Orthonormal Representations for Graph Transduction 210 C #80
Robust Portfolio Optimization 210 C #82
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks 210 C #6
Fast and Accurate Inference of Plackett–Luce Models 210 C #49
Robust Feature-Sample Linear Discriminant Analysis for Brain Disorders Diagnosis 210 C #30
On the Limitation of Spectral Methods: From the Gaussian Hidden Clique Problem to Rank-One Perturbations of Gaussian Tensors 210 C #87
Texture Synthesis Using Convolutional Neural Networks 210 C #1
Smooth and Strong: MAP Inference with Linear Convergence 210 C #78
Accelerated Proximal Gradient Methods for Nonconvex Programming 210 C #96
3D Object Proposals for Accurate Object Class Detection 210 C #12
Individual Planning in Infinite-Horizon Multiagent Settings: Inference, Structure and Scalability 210 C #102
Estimating Mixture Models via Mixtures of Polynomials 210 C #70
Deep Knowledge Tracing 210 C #22
Rethinking LDA: Moment Matching for Discrete ICA 210 C #39
A Nonconvex Optimization Framework for Low Rank Matrix Estimation 210 C #101
Black-box optimization of noisy functions with unknown smoothness 210 C #89
Poster Session
Monotone k-Submodular Function Maximization with Size Constraints 210 C #77
Subspace Clustering with Irrelevant Features via Robust Dantzig Selector 210 C #75
Fast Randomized Kernel Ridge Regression with Statistical Guarantees 210 C #84
GAP Safe screening rules for sparse multi-task and multi-class models 210 C #67
Statistical Model Criticism using Kernel Two Sample Tests 210 C #25
Bidirectional Recurrent Neural Networks as Generative Models 210 C #19
Hessian-free Optimization for Learning Deep Multidimensional Recurrent Neural Networks 210 C #32
Convolutional Neural Networks with Intra-Layer Recurrent Connections for Scene Labeling 210 C #2
Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis 210 C #7
Scalable Adaptation of State Complexity for Nonparametric Hidden Markov Models 210 C #29
Matrix Completion from Fewer Entries: Spectral Detectability and Rank Estimation 210 C #72
Lifted Symmetry Detection and Breaking for MAP Inference 210 C #59
Bandits with Unobserved Confounders: A Causal Approach 210 C #60
Fast Second Order Stochastic Backpropagation for Variational Inference 210 C #38
Scalable Inference for Gaussian Process Models with Black-Box Likelihoods 210 C #33
Probabilistic Variational Bounds for Graphical Models 210 C #63
Combinatorial Cascading Bandits 210 C #90
BACKSHIFT: Learning causal cyclic graphs from unknown shift interventions 210 C #50
Regularized EM Algorithms: A Unified Framework and Statistical Guarantees 210 C #88
Sum-of-Squares Lower Bounds for Sparse PCA 210 C #92
Halting in Random Walk Kernels 210 C #56
Infinite Factorial Dynamical Model 210 C #35
Communication Complexity of Distributed Convex Learning and Optimization 210 C #99
Regressive Virtual Metric Learning 210 C #55
Learning to Transduce with Unbounded Memory 210 C #16
Generative Image Modeling Using Spatial LSTMs 210 C #5
Robust PCA with compressed data 210 C #73
Supervised Learning for Dynamical System Learning 210 C #41
Fast Two-Sample Testing with Analytic Representations of Probability Measures 210 C #53
Anytime Influence Bounds and the Explosive Behavior of Continuous-Time Diffusion Networks 210 C #69
Learning with a Wasserstein Loss 210 C #47
Adaptive Primal-Dual Splitting Methods for Statistical Learning and Image Processing 210 C #91
An Active Learning Framework using Sparse-Graph Codes for Sparse Polynomials and Graph Sketching 210 C #65
Variational Information Maximisation for Intrinsically Motivated Reinforcement Learning 210 C #36
Mixed Robust/Average Submodular Partitioning: Fast Algorithms, Guarantees, and Applications 210 C #74
Tractable Learning for Complex Probability Queries 210 C #44
StopWasting My Gradients: Practical SVRG 210 C #79
On the Convergence of Stochastic Gradient MCMC Algorithms with High-Order Integrators 210 C #64
Are You Talking to a Machine? Dataset and Methods for Multilingual Image Question 210 C #9
Learning spatiotemporal trajectories from manifold-valued longitudinal data 210 C #31
A Bayesian Framework for Modeling Confidence in Perceptual Decision Making 210 C #27
Spectral Representations for Convolutional Neural Networks 210 C #17
Online Gradient Boosting 210 C #93
Deep Temporal Sigmoid Belief Networks for Sequence Modeling 210 C #23

 Tue Dec 08, 2015

Time 210D Level 2 room 210 AB Room 210 AB Room 210 A 210 C #20 210 C #18 210 C #24 210 C #98 210 C #81 210 C #34 210 C #71 210 C #46 210 C #85 210 C #54 210 C #3 210 C #94 210 C #83 210 C #51 210 C #58 210 C #8 210 C #21 210 C #10 210 C #97 210 C #95 210 C #13 210 C #61 210 C #15 210 C #11 210 C #100 210 C #68 210 C #66 210 C #76 210 C #57 210 C #48 210 C #14 210 C #52 210 C #28 210 C #26 210 C #40 210 C #43 210 C #42 210 C #4 210 C #37 210 C #45 210 C #80 210 C #82 210 C #6 210 C #49 210 C #30 210 C #87 210 C #1 210 C #78 210 C #96 210 C #12 210 C #70 210 C #22 210 C #39 210 C #101 210 C #89 210 C #77 210 C #75 210 C #84 210 C #67 210 C #25 210 C #19 210 C #32 210 C #2 210 C #7 210 C #29 210 C #72 210 C #59 210 C #60 210 C #38 210 C #33 210 C #63 210 C #90 210 C #50 210 C #88 210 C #86 210 C #92 210 C #56 210 C #35 210 C #99 210 C #55 210 C #16 210 C #5 210 C #73 210 C #41 210 C #53 210 C #69 210 C #47 210 C #91 210 C #65 210 C #36 210 C #74 210 C #44 210 C #79 210 C #64 210 C #9 210 C #31 210 C #27 210 C #17 210 C #93 210 C #23
09:00 AM (Invited Talks)
Probabilistic Machine Learning: Foundations and Frontiers
09:50 AM (Orals)
Oral Session 1
Randomized Block Krylov Methods for Stronger and Faster Approximate Singular Value Decomposition
10:10 AM (Spotlights)
Spotlight Session 1
10:55 AM (Orals)
Solving Random Quadratic Systems of Equations Is Nearly as Easy as Solving Linear Systems
Sampling from Probabilistic Submodular Models
11:35 AM (Spotlights)
Spotlight Session 2
02:00 PM (Invited Talks)
Incremental Methods for Additive Cost Convex Optimization
02:50 PM (Orals)
Probabilistic Line Searches for Stochastic Optimization
COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution
03:30 PM (Spotlights)
Spotlight Session 3
04:30 PM (Orals)
Oral Session 4
Competitive Distribution Estimation: Why is Good-Turing Good
Fast Convergence of Regularized Learning in Games
Interactive Control of Diverse Complex Characters with Neural Networks
05:30 PM (Spotlights)
Spotlight Session 4
07:00 PM (Demonstrations, Posters)
Too many events to display and no session is defined.
The Brain Uses Reliability of Stimulus Information when Making Perceptual Decisions 210 C #20
Tensorizing Neural Networks 210 C #18
The Human Kernel 210 C #24
On Elicitation Complexity 210 C #98
b-bit Marginal Regression 210 C #81
Automatic Variational Inference in Stan 210 C #34
Submodular Hamming Metrics 210 C #71
Parallel Predictive Entropy Search for Batch Global Optimization of Expensive Objective Functions 210 C #46
Closed-form Estimators for High-dimensional Generalized Linear Models 210 C #85
Inference for determinantal point processes without spectral knowledge 210 C #54
Learning Structured Output Representation using Deep Conditional Generative Models 210 C #3
Super-Resolution Off the Grid 210 C #94
Randomized Block Krylov Methods for Stronger and Faster Approximate Singular Value Decomposition 210 C #83
Policy Evaluation Using the Ω-Return 210 C #51
Scale Up Nonlinear Component Analysis with Doubly Stochastic Gradients 210 C #58
Galileo: Perceiving Physical Object Properties by Integrating a Physics Engine with Deep Learning 210 C #8
Unlocking neural population non-stationarities using hierarchical dynamics models 210 C #21
Character-level Convolutional Networks for Text Classification 210 C #10
Fast Convergence of Regularized Learning in Games 210 C #97
Optimal Rates for Random Fourier Features 210 C #95
Interactive Control of Diverse Complex Characters with Neural Networks 210 C #13
Top-k Multiclass SVM 210 C #61
Unsupervised Learning by Program Synthesis 210 C #15
Winner-Take-All Autoencoders 210 C #11
Structured Estimation with Atomic Norms: General Bounds and Applications 210 C #100
Evaluating the statistical significance of biclusters 210 C #68
Parallel Correlation Clustering on Big Graphs 210 C #66
Alternating Minimization for Regression Problems with Vector-valued Outputs 210 C #76
Frank-Wolfe Bayesian Quadrature: Probabilistic Integration with Theoretical Guarantees 210 C #57
On some provably correct cases of variational inference for topic models 210 C #48
Biologically Inspired Dynamic Textures for Probing Motion Perception 210 C #14
Community Detection via Measure Space Embedding 210 C #52
The Population Posterior and Bayesian Modeling on Streams 210 C #28
High-dimensional neural spike train analysis with generalized count linear dynamical systems 210 C #26
Probabilistic Line Searches for Stochastic Optimization 210 C #40
Reflection, Refraction, and Hamiltonian Monte Carlo 210 C #43
Tree-Guided MCMC Inference for Normalized Random Measure Mixture Models 210 C #42
Expressing an Image Stream with a Sequence of Natural Sentences 210 C #4
Deep learning with Elastic Averaging SGD 210 C #37
Learning Bayesian Networks with Thousands of Variables 210 C #45
Minimum Weight Perfect Matching via Blossom Belief Propagation 210 C #80
LASSO with Non-linear Measurements is Equivalent to One With Linear Measurements 210 C #82
Bidirectional Recurrent Convolutional Networks for Multi-Frame Super-Resolution 210 C #6
Large-scale probabilistic predictors with and without guarantees of validity 210 C #49
Preconditioned Spectral Descent for Deep Learning 210 C #30
Semi-Proximal Mirror-Prox for Nonsmooth Composite Minimization 210 C #87
Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks 210 C #1
Subset Selection by Pareto Optimization 210 C #78
Combinatorial Bandits Revisited 210 C #96
Learning both Weights and Connections for Efficient Neural Network 210 C #12
Sampling from Probabilistic Submodular Models 210 C #70
Deeply Learning the Messages in Message Passing Inference 210 C #22
Linear Response Methods for Accurate Covariance Estimates from Mean Field Variational Bayes 210 C #39
Subsampled Power Iteration: a Unified Algorithm for Block Models and Planted CSP's 210 C #101
A Universal Primal-Dual Convex Optimization Framework 210 C #89
On Variance Reduction in Stochastic Gradient Descent and its Asynchronous Variants 210 C #77
SGD Algorithms based on Incomplete U-statistics: Large-Scale Minimization of Empirical Risk 210 C #75
On the Pseudo-Dimension of Nearly Optimal Auctions 210 C #84
Fast Bidirectional Probability Estimation in Markov Models 210 C #67
Latent Bayesian melding for integrating individual and population models 210 C #25
Training Restricted Boltzmann Machine via the Thouless-Anderson-Palmer free energy 210 C #19
Learning Stationary Time Series using Gaussian Processes with Nonparametric Kernels 210 C #32
Shepard Convolutional Neural Networks 210 C #2
SubmodBoxes: Near-Optimal Search for a Set of Diverse Object Proposals 210 C #7
Probabilistic Curve Learning: Coulomb Repulsion and the Electrostatic Gaussian Process 210 C #29
Extending Gossip Algorithms to Distributed Estimation of U-statistics 210 C #72
The Self-Normalized Estimator for Counterfactual Learning 210 C #59
Distributionally Robust Logistic Regression 210 C #60
Learning with Group Invariant Features: A Kernel Perspective. 210 C #38
Path-SGD: Path-Normalized Optimization in Deep Neural Networks 210 C #33
Asynchronous Parallel Stochastic Gradient for Nonconvex Optimization 210 C #63
Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning 210 C #90
On the Accuracy of Self-Normalized Log-Linear Models 210 C #50
Competitive Distribution Estimation: Why is Good-Turing Good 210 C #88
Fast, Provable Algorithms for Isotonic Regression in all L_p-norms 210 C #86
HONOR: Hybrid Optimization for NOn-convex Regularized problems 210 C #92
Matrix Manifold Optimization for Gaussian Mixtures 210 C #56
Data Generation as Sequential Decision Making 210 C #35
Online Learning with Adversarial Delays 210 C #99
Sample Complexity of Learning Mahalanobis Distance Metrics 210 C #55
Deep Poisson Factor Modeling 210 C #16
Visalogy: Answering Visual Analogy Questions 210 C #5
Newton-Stein Method: A Second Order Method for GLMs via Stein's Lemma 210 C #73
A hybrid sampler for Poisson-Kingman mixture models 210 C #41
The Consistency of Common Neighbors for Link Prediction in Stochastic Blockmodels 210 C #53
Regularization Path of Cross-Validation Error Lower Bounds 210 C #69
Rapidly Mixing Gibbs Sampling for a Class of Factor Graphs Using Hierarchy Width 210 C #47
Private Graphon Estimation for Sparse Graphs 210 C #91
Distributed Submodular Cover: Succinctly Summarizing Massive Data 210 C #65
Stochastic Expectation Propagation 210 C #36
Collaboratively Learning Preferences from Ordinal Data 210 C #74
Planar Ultrametrics for Image Segmentation 210 C #44
Interpolating Convex and Non-Convex Tensor Decompositions via the Subspace Norm 210 C #79
Solving Random Quadratic Systems of Equations Is Nearly as Easy as Solving Linear Systems 210 C #64
Learning visual biases from human imagination 210 C #9
Learning Continuous Control Policies by Stochastic Value Gradients 210 C #31
Efficient Learning of Continuous-Time Hidden Markov Models for Disease Progression 210 C #27
Large-Scale Bayesian Multi-Label Learning via Topic-Based Label Embeddings 210 C #17
A Convergent Gradient Descent Algorithm for Rank Minimization and Semidefinite Programming from Random Linear Measurements 210 C #93
COEVOLVE: A Joint Point Process Model for Information Diffusion and Network Co-evolution 210 C #23

 Wed Dec 09, 2015

Time 210D Level 2 room 210 AB Room 210 A 210 C #20 210 C #18 210 C #24 210 C #98 210 C #81 210 C #34 210 C #71 210 C #46 210 C #85 210 C #54 210 C #3 210 C #94 210 C #83 210 C #51 210 C #62 210 C #58 210 C #8 210 C #21 210 C #10 210 C #97 210 C #95 210 C #13 210 C #61 210 C #15 210 C #11 210 C #100 210 C #68 210 C #66 210 C #76 210 C #57 210 C #48 210 C #14 210 C #52 210 C #28 210 C #26 210 C #40 210 C #43 210 C #42 210 C #4 210 C #37 210 C #45 210 C #80 210 C #82 210 C #6 210 C #49 210 C #30 210 C #87 210 C #1 210 C #78 210 C #96 210 C #12 210 C #70 210 C #22 210 C #39 210 C #89 210 C #77 210 C #75 210 C #84 210 C #67 210 C #25 210 C #19 210 C #32 210 C #2 210 C #7 210 C #29 210 C #72 210 C #59 210 C #60 210 C #38 210 C #33 210 C #63 210 C #90 210 C #50 210 C #88 210 C #86 210 C #92 210 C #56 210 C #35 210 C #99 210 C #55 210 C #16 210 C #5 210 C #73 210 C #41 210 C #53 210 C #69 210 C #47 210 C #91 210 C #65 210 C #36 210 C #74 210 C #44 210 C #79 210 C #64 210 C #9 210 C #31 210 C #27 210 C #17 210 C #93 210 C #23 220 A
09:00 AM (Invited Talks)
Post-selection Inference for Forward Stepwise Regression, Lasso and other Adaptive Statistical procedures
09:50 AM (Orals)
Oral Session 5
Learning Theory and Algorithms for Forecasting Non-stationary Time Series
10:10 AM (Spotlights)
Spotlight Session 5
10:30 AM (Breaks)
Breakfast
10:55 AM (Orals)
Oral Session 6
Deep Visual Analogy-Making
End-To-End Memory Networks
11:35 AM (Spotlights)
Spotlight Session 6
02:00 PM (Invited Talks)
Diagnosis and Therapy of Psychiatric Disorders Based on Brain Dynamics
02:50 PM (Orals)
A Reduced-Dimension fMRI Shared Response Model
Attractor Network Dynamics Enable Preplay and Rapid Path Planning in Maze–like Environments
03:30 PM (Spotlights)
Spotlight Session 7
04:30 PM (Invited Talks)
Computational Principles for Deep Neuronal Architectures
05:20 PM (Orals)
Oral Session 8
Efficient Exact Gradient Update for training Deep Networks with Very Large Sparse Targets
05:40 PM (Spotlights)
Spotlight Session 8