Search Schedule »

Show All »
Dec. 2, 2018 Expo schedule » New in ML »

Timezone: America/Montreal »

Indicates the beginning of a session

 Wed Dec 05, 2018

Time Room 210 Room 517 AB
05:00 PM (Posters)
Equality of Opportunity in Classification: A Causal Approach Room 210 #1
Confounding-Robust Policy Improvement Room 210 #2
Causal Discovery from Discrete Data using Hidden Compact Representation Room 210 #3
Dirichlet belief networks for topic structure learning Room 210 #4
Approximate Knowledge Compilation by Online Collapsed Importance Sampling Room 210 #5
Proximal Graphical Event Models Room 210 #6
Dynamic Network Model from Partial Observations Room 210 #7
HOGWILD!-Gibbs can be PanAccurate Room 210 #8
DAGs with NO TEARS: Continuous Optimization for Structure Learning Room 210 #9
Mean Field for the Stochastic Blockmodel: Optimization Landscape and Convergence Issues Room 210 #10
Coupled Variational Bayes via Optimization Embedding Room 210 #11
Stochastic Nonparametric Event-Tensor Decomposition Room 210 #12
GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration Room 210 #13
Heterogeneous Multi-output Gaussian Process Prediction Room 210 #14
Probabilistic Matrix Factorization for Automated Machine Learning Room 210 #15
Stochastic Expectation Maximization with Variance Reduction Room 210 #16
Generative Neural Machine Translation Room 210 #17
Variational Learning on Aggregate Outputs with Gaussian Processes Room 210 #19
Learning Invariances using the Marginal Likelihood Room 210 #20
Dirichlet-based Gaussian Processes for Large-scale Calibrated Classification Room 210 #21
Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior Room 210 #22
Efficient High Dimensional Bayesian Optimization with Additivity and Quadrature Fourier Features Room 210 #23
Adversarially Robust Optimization with Gaussian Processes Room 210 #24
Multi-objective Maximization of Monotone Submodular Functions with Cardinality Constraint Room 210 #25
Variational PDEs for Acceleration on Manifolds and Application to Diffeomorphisms Room 210 #26
Zeroth-order (Non)-Convex Stochastic Optimization via Conditional Gradient and Gradient Updates Room 210 #27
Computing Higher Order Derivatives of Matrix and Tensor Expressions Room 210 #28
How SGD Selects the Global Minima in Over-parameterized Learning: A Dynamical Stability Perspective Room 210 #29
The Effect of Network Width on the Performance of Large-batch Training Room 210 #30
COLA: Decentralized Linear Learning Room 210 #31
Distributed Stochastic Optimization via Adaptive SGD Room 210 #32
Non-Ergodic Alternating Proximal Augmented Lagrangian Algorithms with Optimal Rates Room 210 #33
Breaking the Span Assumption Yields Fast Finite-Sum Minimization Room 210 #34
Optimization for Approximate Submodularity Room 210 #35
Submodular Maximization via Gradient Ascent: The Case of Deep Submodular Functions Room 210 #36
Maximizing Induced Cardinality Under a Determinantal Point Process Room 210 #37
Efficient Algorithms for Non-convex Isotonic Regression through Submodular Optimization Room 210 #38
Revisiting Decomposable Submodular Function Minimization with Incidence Relations Room 210 #39
Coordinate Descent with Bandit Sampling Room 210 #40
Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization Room 210 #41
Stochastic Cubic Regularization for Fast Nonconvex Optimization Room 210 #42
On the Local Minima of the Empirical Risk Room 210 #43
Stochastic Nested Variance Reduced Gradient Descent for Nonconvex Optimization Room 210 #44
NEON2: Finding Local Minima via First-Order Oracles Room 210 #45
How Much Restricted Isometry is Needed In Nonconvex Matrix Recovery? Room 210 #46
Escaping Saddle Points in Constrained Optimization Room 210 #47
Analysis of Krylov Subspace Solutions of Regularized Non-Convex Quadratic Problems Room 210 #48
SPIDER: Near-Optimal Non-Convex Optimization via Stochastic Path-Integrated Differential Estimator Room 210 #49
Natasha 2: Faster Non-Convex Optimization Than SGD Room 210 #50
Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization Room 210 #51
Structured Local Minima in Sparse Blind Deconvolution Room 210 #52
Algorithmic Regularization in Learning Deep Homogeneous Models: Layers are Automatically Balanced Room 210 #53
Are ResNets Provably Better than Linear Predictors? Room 210 #54
Adaptive Methods for Nonconvex Optimization Room 210 #55
Alternating optimization of decision trees, with application to learning sparse oblique trees Room 210 #56
GILBO: One Metric to Measure Them All Room 210 #57
Isolating Sources of Disentanglement in Variational Autoencoders Room 210 #58
On GANs and GMMs Room 210 #59
Assessing Generative Models via Precision and Recall Room 210 #60
Gather-Excite: Exploiting Feature Context in Convolutional Neural Networks Room 210 #61
Uncertainty-Aware Attention for Reliable Interpretation and Prediction Room 210 #62
Forecasting Treatment Responses Over Time Using Recurrent Marginal Structural Networks Room 210 #63
Backpropagation with Callbacks: Foundations for Efficient and Expressive Differentiable Programming Room 210 #64
Recurrent World Models Facilitate Policy Evolution Room 210 #65
Long short-term memory and Learning-to-learn in networks of spiking neurons Room 210 #66
Distributed Weight Consolidation: A Brain Segmentation Case Study Room 210 #67
Learning to Play With Intrinsically-Motivated, Self-Aware Agents Room 210 #68
Gradient Descent for Spiking Neural Networks Room 210 #69
Demystifying excessively volatile human learning: A Bayesian persistent prior and a neural approximation Room 210 #70
Temporal alignment and latent Gaussian process factor inference in population spike trains Room 210 #71
Information-based Adaptive Stimulus Selection to Optimize Communication Efficiency in Brain-Computer Interfaces Room 210 #72
Model-based targeted dimensionality reduction for neuronal population data Room 210 #73
Objective and efficient inference for couplings in neuronal networks Room 210 #74
The emergence of multiple retinal cell types through efficient coding of natural movies Room 210 #75
Benefits of over-parameterization with EM Room 210 #76
On Coresets for Logistic Regression Room 210 #77
On Learning Markov Chains Room 210 #78
Contextual Stochastic Block Models Room 210 #79
Estimators for Multivariate Information Measures in General Probability Spaces Room 210 #80
Blind Deconvolutional Phase Retrieval via Convex Programming Room 210 #81
Entropy Rate Estimation for Markov Chains with Large State Space Room 210 #82
Bandit Learning in Concave N-Person Games Room 210 #83
Depth-Limited Solving for Imperfect-Information Games Room 210 #84
The Physical Systems Behind Optimization Algorithms Room 210 #85
The Nearest Neighbor Information Estimator is Adaptively Near Minimax Rate-Optimal Room 210 #86
Robust Learning of Fixed-Structure Bayesian Networks Room 210 #87
Information-theoretic Limits for Community Detection in Network Models Room 210 #88
Generalizing Graph Matching beyond Quadratic Assignment Model Room 210 #89
Improving Simple Models with Confidence Profiles Room 210 #90
Online Learning with an Unknown Fairness Metric Room 210 #91
Legendre Decomposition for Tensors Room 210 #92
The Price of Privacy for Low-rank Factorization Room 210 #93
Empirical Risk Minimization in Non-interactive Local Differential Privacy Revisited Room 210 #94
Differentially Private Change-Point Detection Room 210 #95
Scalable Laplacian K-modes Room 210 #96
Geometrically Coupled Monte Carlo Sampling Room 210 #97
Continuous-time Value Function Approximation in Reproducing Kernel Hilbert Spaces Room 210 #98
Faster Online Learning of Optimal Threshold for Consistent F-measure Optimization Room 210 #99
Reducing Network Agnostophobia Room 210 #100
Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies Room 517 AB #101
Near-Optimal Policies for Dynamic Multinomial Logit Assortment Selection Models Room 517 AB #102
The Everlasting Database: Statistical Validity at a Fair Price Room 517 AB #103
Scalar Posterior Sampling with Applications Room 517 AB #104
Iterative Value-Aware Model Learning Room 517 AB #105
A Lyapunov-based Approach to Safe Reinforcement Learning Room 517 AB #106
Temporal Regularization for Markov Decision Process Room 517 AB #107
Maximum Causal Tsallis Entropy Imitation Learning Room 517 AB #108
Policy Optimization via Importance Sampling Room 517 AB #109
Reinforcement Learning of Theorem Proving Room 517 AB #110
Simple random search of static linear policies is competitive for reinforcement learning Room 517 AB #111
Meta-Gradient Reinforcement Learning Room 517 AB #112
Reinforcement Learning for Solving the Vehicle Routing Problem Room 517 AB #113
Learn What Not to Learn: Action Elimination with Deep Reinforcement Learning Room 517 AB #114
REFUEL: Exploring Sparse Features in Deep Reinforcement Learning for Fast Disease Diagnosis Room 517 AB #115
Learning Plannable Representations with Causal InfoGAN Room 517 AB #116
Improving Exploration in Evolution Strategies for Deep Reinforcement Learning via a Population of Novelty-Seeking Agents Room 517 AB #117
Transfer of Deep Reactive Policies for MDP Planning Room 517 AB #118
Q-learning with Nearest Neighbors Room 517 AB #119
Distributed Multitask Reinforcement Learning with Quadratic Convergence Room 517 AB #120
Breaking the Curse of Horizon: Infinite-Horizon Off-Policy Estimation Room 517 AB #121
Constrained Cross-Entropy Method for Safe Reinforcement Learning Room 517 AB #122
Representation Balancing MDPs for Off-policy Policy Evaluation Room 517 AB #123
Dual Policy Iteration Room 517 AB #124
Occam's razor is insufficient to infer the preferences of irrational agents Room 517 AB #125
Transfer of Value Functions via Variational Methods Room 517 AB #126
Reinforcement Learning with Multiple Experts: A Bayesian Model Combination Approach Room 517 AB #127
Online Robust Policy Learning in the Presence of Unknown Adversaries Room 517 AB #128
A Bayesian Approach to Generative Adversarial Imitation Learning Room 517 AB #129
Verifiable Reinforcement Learning via Policy Extraction Room 517 AB #130
Deep Reinforcement Learning of Marked Temporal Point Processes Room 517 AB #131
On Learning Intrinsic Rewards for Policy Gradient Methods Room 517 AB #132
Evolution-Guided Policy Gradient in Reinforcement Learning Room 517 AB #133
Meta-Reinforcement Learning of Structured Exploration Strategies Room 517 AB #134
Diversity-Driven Exploration Strategy for Deep Reinforcement Learning Room 517 AB #135
Genetic-Gated Networks for Deep Reinforcement Learning Room 517 AB #136
Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing Room 517 AB #137
Hardware Conditioned Policies for Multi-Robot Transfer Learning Room 517 AB #138
Reward learning from human preferences and demonstrations in Atari Room 517 AB #139
Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation Room 517 AB #140
Visual Reinforcement Learning with Imagined Goals Room 517 AB #141
Playing hard exploration games by watching YouTube Room 517 AB #142
Unsupervised Video Object Segmentation for Deep Reinforcement Learning Room 517 AB #143
Learning to Navigate in Cities Without a Map Room 517 AB #144
Learning Abstract Options Room 517 AB #145
Object-Oriented Dynamics Predictor Room 517 AB #146
A Deep Bayesian Policy Reuse Approach Against Non-Stationary Agents Room 517 AB #147
Learning Attentional Communication for Multi-Agent Cooperation Room 517 AB #148
Deep Dynamical Modeling and Control of Unsteady Fluid Flows Room 517 AB #149
Adaptive Skip Intervals: Temporal Abstraction for Recurrent Dynamical Models Room 517 AB #150
Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning Room 517 AB #151
Total stochastic gradient algorithms and applications in reinforcement learning Room 517 AB #152
Fighting Boredom in Recommender Systems with Linear Reinforcement Learning Room 517 AB #153
Randomized Prior Functions for Deep Reinforcement Learning Room 517 AB #154
Scalable Coordinated Exploration in Concurrent Reinforcement Learning Room 517 AB #155
Context-dependent upper-confidence bounds for directed exploration Room 517 AB #156
Multi-Agent Generative Adversarial Imitation Learning Room 517 AB #157
Actor-Critic Policy Optimization in Partially Observable Multiagent Environments Room 517 AB #158
Learning to Share and Hide Intentions using Information Regularization Room 517 AB #159
Credit Assignment For Collective Multiagent RL With Global Rewards Room 517 AB #160
Multi-Agent Reinforcement Learning via Double Averaging Primal-Dual Optimization Room 517 AB #161
Learning Others' Intentional Models in Multi-Agent Settings Using Interactive POMDPs Room 517 AB #162
Bayesian Control of Large MDPs with Unknown Dynamics in Data-Poor Environments Room 517 AB #163
Negotiable Reinforcement Learning for Pareto Optimal Sequential Decision-Making Room 517 AB #164
rho-POMDPs have Lipschitz-Continuous epsilon-Optimal Value Functions Room 517 AB #165
Learning Task Specifications from Demonstrations Room 517 AB #166
Teaching Inverse Reinforcement Learners via Features and Demonstrations Room 517 AB #167
Single-Agent Policy Tree Search With Guarantees Room 517 AB #168
From Stochastic Planning to Marginal MAP Room 517 AB #169
Dual Principal Component Pursuit: Improved Analysis and Efficient Algorithms Room 517 AB #170