Search Schedule »

Show All »

Timezone: Europe/Stockholm »

Indicates the beginning of a session

 Thu Jul 12, 2018

Time Hall B
06:15 PM (Posters)
Large-Scale Sparse Inverse Covariance Estimation via Thresholding and Max-Det Matrix Completion Hall B #1
Robust and Scalable Models of Microbiome Dynamics Hall B #2
Explicit Inductive Bias for Transfer Learning with Convolutional Networks Hall B #3
GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks Hall B #4
Optimizing the Latent Space of Generative Networks Hall B #5
Theoretical Analysis of Image-to-Image Translation with Adversarial Learning Hall B #6
Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor Hall B #7
PIPPS: Flexible Model-Based Policy Search Robust to the Curse of Chaos Hall B #8
Probabilistic Recurrent State-Space Models Hall B #9
Structured Variationally Auto-encoded Optimization Hall B #10
A Robust Approach to Sequential Information Theoretic Planning Hall B #11
Error Estimation for Randomized Least-Squares Algorithms via the Bootstrap Hall B #12
Distributed Asynchronous Optimization with Unbounded Delays: How Slow Can You Go? Hall B #13
Error Compensated Quantized SGD and its Applications to Large-scale Distributed Optimization Hall B #14
Low-Rank Riemannian Optimization on Positive Semidefinite Stochastic Matrices with Applications to Graph Clustering Hall B #15
Dissecting Adam: The Sign, Magnitude and Variance of Stochastic Gradients Hall B #16
Discovering and Removing Exogenous State Variables and Rewards for Reinforcement Learning Hall B #17
Differentially Private Database Release via Kernel Mean Embeddings Hall B #18
Extracting Automata from Recurrent Neural Networks Using Queries and Counterexamples Hall B #19
Neural Dynamic Programming for Musical Self Similarity Hall B #20
Learning long term dependencies via Fourier recurrent units Hall B #21
Autoregressive Convolutional Neural Networks for Asynchronous Time Series Hall B #22
Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation Hall B #23
Regret Minimization for Partially Observable Deep Reinforcement Learning Hall B #24
Goodness-of-fit Testing for Discrete Distributions via Stein Discrepancy Hall B #25
Unbiased Objective Estimation in Predictive Optimization Hall B #26
Ultra Large-Scale Feature Selection using Count-Sketches Hall B #27
Matrix Norms in Data Streams: Faster, Multi-Pass and Row-Order Hall B #28
Can Deep Reinforcement Learning Solve Erdos-Selfridge-Spencer Games? Hall B #29
The Mirage of Action-Dependent Baselines in Reinforcement Learning Hall B #30
Composite Marginal Likelihood Methods for Random Utility Models Hall B #31
Ranking Distributions based on Noisy Sorting Hall B #32
DICOD: Distributed Convolutional Coordinate Descent for Convolutional Sparse Coding Hall B #33
Exploring Hidden Dimensions in Accelerating Convolutional Neural Networks Hall B #34
Deep Models of Interactions Across Sets Hall B #35
ContextNet: Deep learning for Star Galaxy Classification Hall B #36
First Order Generative Adversarial Networks Hall B #37
Max-Mahalanobis Linear Discriminant Analysis Networks Hall B #38
Learning Maximum-A-Posteriori Perturbation Models for Structured Prediction in Polynomial Time Hall B #39
Structured Output Learning with Abstention: Application to Accurate Opinion Prediction Hall B #40
SBEED: Convergent Reinforcement Learning with Nonlinear Function Approximation Hall B #41
Smoothed Action Value Functions for Learning Gaussian Policies Hall B #42
Towards End-to-End Prosody Transfer for Expressive Speech Synthesis with Tacotron Hall B #43
Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesis Hall B #44
AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning Hall B #45
TAPAS: Tricks to Accelerate (encrypted) Prediction As a Service Hall B #46
End-to-End Learning for the Deep Multivariate Probit Model Hall B #47
Differentiable Dynamic Programming for Structured Prediction and Attention Hall B #48
Optimal Distributed Learning with Multi-pass Stochastic Gradient Methods Hall B #49
Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates Hall B #50
SQL-Rank: A Listwise Approach to Collaborative Ranking Hall B #51
Extreme Learning to Rank via Low Rank Assumption Hall B #52
Adversarial Attack on Graph Structured Data Hall B #53
Reinforcing Adversarial Robustness using Model Confidence Induced by Adversarial Training Hall B #54
Closed-form Marginal Likelihood in Gamma-Poisson Matrix Factorization Hall B #55
Learning Binary Latent Variable Models: A Tensor Eigenpair Approach Hall B #56
Thompson Sampling for Combinatorial Semi-Bandits Hall B #57
Let’s be Honest: An Optimal No-Regret Framework for Zero-Sum Games Hall B #58
Deep Asymmetric Multi-task Feature Learning Hall B #59
Learn from Your Neighbor: Learning Multi-modal Mappings from Sparse Annotations Hall B #60
Stein Variational Message Passing for Continuous Graphical Models Hall B #61
Discrete-Continuous Mixtures in Probabilistic Programming: Generalized Semantics and Inference Algorithms Hall B #62
Towards Binary-Valued Gates for Robust LSTM Training Hall B #63
Fitting New Speakers Based on a Short Untranscribed Sample Hall B #64
Stochastic Variance-Reduced Policy Gradient Hall B #65
Convergent Tree Backup and Retrace with Function Approximation Hall B #66
Alternating Randomized Block Coordinate Descent Hall B #67
Shampoo: Preconditioned Stochastic Tensor Optimization Hall B #68
Stochastic Wasserstein Barycenters Hall B #69
Accelerating Natural Gradient with Higher-Order Invariance Hall B #70
Learning unknown ODE models with Gaussian processes Hall B #71
Constraining the Dynamics of Deep Probabilistic Models Hall B #72
Fast Decoding in Sequence Models Using Discrete Latent Variables Hall B #73
High Performance Zero-Memory Overhead Direct Convolutions Hall B #74
Approximate Leave-One-Out for Fast Parameter Tuning in High Dimensions Hall B #75
Improved large-scale graph learning through ridge spectral sparsification Hall B #76
Distilling the Posterior in Bayesian Neural Networks Hall B #77
Scalable approximate Bayesian inference for particle tracking data Hall B #78
Weakly Consistent Optimal Pricing Algorithms in Repeated Posted-Price Auctions with Strategic Buyer Hall B #79
Practical Contextual Bandits with Regression Oracles Hall B #80
Stochastic Variance-Reduced Hamilton Monte Carlo Methods Hall B #81
Asynchronous Stochastic Quasi-Newton MCMC for Non-Convex Optimization Hall B #82
GAIN: Missing Data Imputation using Generative Adversarial Nets Hall B #83
Synthesizing Programs for Images using Reinforced Adversarial Learning Hall B #84
Geometry Score: A Method For Comparing Generative Adversarial Networks Hall B #85
Addressing Function Approximation Error in Actor-Critic Methods Hall B #86
Fast Bellman Updates for Robust MDPs Hall B #87
Configurable Markov Decision Processes Hall B #88
Prediction Rule Reshaping Hall B #89
Dimensionality-Driven Learning with Noisy Labels Hall B #90
Learning Memory Access Patterns Hall B #91
Geodesic Convolutional Shape Optimization Hall B #92
Visualizing and Understanding Atari Agents Hall B #93
An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning Hall B #94
Is Generator Conditioning Causally Related to GAN Performance? Hall B #95
K-Beam Minimax: Efficient Optimization for Deep Adversarial Learning Hall B #96
Inductive Two-Layer Modeling with Parametric Bregman Transfer Hall B #97
Does Distributionally Robust Supervised Learning Give Robust Classifiers? Hall B #98
Understanding Generalization and Optimization Performance of Deep CNNs Hall B #99
The Multilinear Structure of ReLU Networks Hall B #100
Parallel and Streaming Algorithms for K-Core Decomposition Hall B #101
Fast Approximate Spectral Clustering for Dynamic Networks Hall B #102
Gradient Descent Learns One-hidden-layer CNN: Don't be Afraid of Spurious Local Minima Hall B #103
Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions Hall B #104
Greed is Still Good: Maximizing Monotone Submodular+Supermodular (BP) Functions Hall B #105
Black-box Adversarial Attacks with Limited Queries and Information Hall B #106
Using Inherent Structures to design Lean 2-layer RBMs Hall B #107
Not to Cry Wolf: Distantly Supervised Multitask Learning in Critical Care Hall B #108
Composable Planning with Attributes Hall B #109
Measuring abstract reasoning in neural networks Hall B #110
Projection-Free Online Optimization with Stochastic Gradient: From Convexity to Submodularity Hall B #111
Self-Bounded Prediction Suffix Tree via Approximate String Matching Hall B #112
MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels Hall B #113
Curriculum Learning by Transfer Learning: Theory and Experiments with Deep Networks Hall B #114
Composite Functional Gradient Learning of Generative Adversarial Models Hall B #115
LaVAN: Localized and Visible Adversarial Noise Hall B #116
Approximation Guarantees for Adaptive Sampling Hall B #117
Constrained Interacting Submodular Groupings Hall B #118
Residual Unfairness in Fair Machine Learning from Prejudiced Data Hall B #119
Adversarial Regression with Multiple Learners Hall B #120
Representation Tradeoffs for Hyperbolic Embeddings Hall B #121
Improving Sign Random Projections With Additional Information Hall B #122
Bandits with Delayed, Aggregated Anonymous Feedback Hall B #123
Make the Minority Great Again: First-Order Regret Bound for Contextual Bandits Hall B #124
Learning Policy Representations in Multiagent Systems Hall B #125
Learning to Coordinate with Coordination Graphs in Repeated Single-Stage Multi-Agent Decision Problems Hall B #126
Beyond Finite Layer Neural Networks: Bridging Deep Architectures and Numerical Differential Equations Hall B #127
Compressing Neural Networks using the Variational Information Bottelneck Hall B #128
Scalable Bilinear Pi Learning Using State and Action Features Hall B #129
Time Limits in Reinforcement Learning Hall B #130
Semi-Supervised Learning on Data Streams via Temporal Label Propagation Hall B #131
Implicit Regularization in Nonconvex Statistical Estimation: Gradient Descent Converges Linearly for Phase Retrieval and Matrix Completion Hall B #132
A Fast and Scalable Joint Estimator for Integrating Additional Knowledge in Learning Multiple Related Sparse Gaussian Graphical Models Hall B #133
Bucket Renormalization for Approximate Inference Hall B #134
Kernel Recursive ABC: Point Estimation with Intractable Likelihood Hall B #135
Modeling Others using Oneself in Multi-Agent Reinforcement Learning Hall B #136
Tropical Geometry of Deep Neural Networks Hall B #137
Learning Dynamics of Linear Denoising Autoencoders Hall B #138
Nonparametric variable importance using an augmented neural network with multi-task learning Hall B #139
Training Neural Machines with Trace-Based Supervision Hall B #140
Open Category Detection with PAC Guarantees Hall B #141
SAFFRON: an Adaptive Algorithm for Online Control of the False Discovery Rate Hall B #142
Learning Localized Spatio-Temporal Models From Streaming Data Hall B #143
Feasible Arm Identification Hall B #144
Fast Maximization of Non-Submodular, Monotonic Functions on the Integer Lattice Hall B #145
Decentralized Submodular Maximization: Bridging Discrete and Continuous Settings Hall B #146
Towards Fast Computation of Certified Robustness for ReLU Networks Hall B #147
A Two-Step Computation of the Exact GAN Wasserstein Distance Hall B #148
Spatio-temporal Bayesian On-line Changepoint Detection with Model Selection Hall B #149
Fast Stochastic AUC Maximization with $O(1/n)$-Convergence Rate Hall B #150
Accurate Uncertainties for Deep Learning Using Calibrated Regression Hall B #151
Neural Autoregressive Flows Hall B #152
Probabilistic Boolean Tensor Decomposition Hall B #153
A Primal-Dual Analysis of Global Optimality in Nonconvex Low-Rank Matrix Recovery Hall B #154
A Delay-tolerant Proximal-Gradient Algorithm for Distributed Learning Hall B #155
Randomized Block Cubic Newton Method Hall B #156
Massively Parallel Algorithms and Hardness for Single-Linkage Clustering under $\ell_p$ Distances Hall B #157
Local Density Estimation in High Dimensions Hall B #158
To Understand Deep Learning We Need to Understand Kernel Learning Hall B #159
Learning in Reproducing Kernel Kreı̆n Spaces Hall B #160
Functional Gradient Boosting based on Residual Network Perception Hall B #161
Binary Classification with Karmic, Threshold-Quasi-Concave Metrics Hall B #162
Characterizing Implicit Bias in Terms of Optimization Geometry Hall B #163
prDeep: Robust Phase Retrieval with a Flexible Deep Network Hall B #164
Adversarial Time-to-Event Modeling Hall B #165
MAGAN: Aligning Biological Manifolds Hall B #166
Multicalibration: Calibration for the (Computationally-Identifiable) Masses Hall B #167
Improving the Privacy and Accuracy of ADMM-Based Distributed Algorithms Hall B #168
PixelSNAIL: An Improved Autoregressive Generative Model Hall B #169
Focused Hierarchical RNNs for Conditional Sequence Processing Hall B #170
Noise2Noise: Learning Image Restoration without Clean Data Hall B #171
Learning to Reweight Examples for Robust Deep Learning Hall B #172
Policy and Value Transfer in Lifelong Reinforcement Learning Hall B #173
GEP-PG: Decoupling Exploration and Exploitation in Deep Reinforcement Learning Algorithms Hall B #174
A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music Hall B #175
Understanding the Loss Surface of Neural Networks for Binary Classification Hall B #176
Dynamical Isometry and a Mean Field Theory of RNNs: Gating Enables Signal Propagation in Recurrent Neural Networks Hall B #177
Reviving and Improving Recurrent Back-Propagation Hall B #178
Riemannian Stochastic Recursive Gradient Algorithm with Retraction and Vector Transport and Its Convergence Analysis Hall B #179
Learning Compact Neural Networks with Regularization Hall B #180
Investigating Human Priors for Playing Video Games Hall B #181
Decoupling Gradient-Like Learning Rules from Representations Hall B #182
Invariance of Weight Distributions in Rectified MLPs Hall B #183
Stronger Generalization Bounds for Deep Nets via a Compression Approach Hall B #184
Near Optimal Frequent Directions for Sketching Dense and Sparse Matrices Hall B #185
Loss Decomposition for Fast Learning in Large Output Spaces Hall B #186
Stochastic Proximal Algorithms for AUC Maximization Hall B #187
Accelerated Spectral Ranking Hall B #188
Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning Hall B #189
Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam Hall B #190
Learning One Convolutional Layer with Overlapping Patches Hall B #191
A Spline Theory of Deep Learning Hall B #192
Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priors Hall B #193
Variational Bayesian dropout: pitfalls and fixes Hall B #194
Adversarial Learning with Local Coordinate Coding Hall B #195
Learning Representations and Generative Models for 3D Point Clouds Hall B #196
Bayesian Uncertainty Estimation for Batch Normalized Deep Networks Hall B #197
Noisy Natural Gradient as Variational Inference Hall B #198
Deep Variational Reinforcement Learning for POMDPs Hall B #199
Recurrent Predictive State Policy Networks Hall B #200
The Mechanics of n-Player Differentiable Games Hall B #201
Improved Training of Generative Adversarial Networks Using Representative Features Hall B #202
Hierarchical Multi-Label Classification Networks Hall B #203
Knowledge Transfer with Jacobian Matching Hall B #204
Towards Black-box Iterative Machine Teaching Hall B #205
Improving the Gaussian Mechanism for Differential Privacy: Analytical Calibration and Optimal Denoising Hall B #206
Importance Weighted Transfer of Samples in Reinforcement Learning Hall B #207
Beyond the One-Step Greedy Approach in Reinforcement Learning Hall B #208
Optimization, fast and slow: optimally switching between local and Bayesian optimization Hall B #209
Batch Bayesian Optimization via Multi-objective Acquisition Ensemble for Automated Analog Circuit Design Hall B #210
Graphical Nonconvex Optimization via an Adaptive Convex Relaxation Hall B #211
Approximate message passing for amplitude based optimization Hall B #212
Tempered Adversarial Networks Hall B #214
Delayed Impact of Fair Machine Learning Hall B #213
Fast Information-theoretic Bayesian Optimisation Hall B #215
Tight Regret Bounds for Bayesian Optimization in One Dimension Hall B #216
Image Transformer Hall B #217
Kernelized Synaptic Weight Matrices Hall B #218
A Distributed Second-Order Algorithm You Can Trust Hall B #219
On Acceleration with Noise-Corrupted Gradients Hall B #220
Gradient Coding from Cyclic MDS Codes and Expander Graphs Hall B #221
Accelerating Greedy Coordinate Descent Methods Hall B #222
Finding Influential Training Samples for Gradient Boosted Decision Trees Hall B #223
Improving Regression Performance with Distributional Losses Hall B #224
QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning Hall B #225
Learning to Act in Decentralized Partially Observable MDPs Hall B #226
Local Convergence Properties of SAGA/Prox-SVRG and Acceleration Hall B #227