Search Schedule »

Show All »
Dec. 8, 2019 Expo schedule » New in ML »

Timezone: America/Vancouver »

Indicates the beginning of a session

 Thu Dec 12, 2019

Time East Exhibition Hall B + C
10:45 AM (Posters)
Deep Learning -- Optimization for Deep Networks
Explaining Landscape Connectivity of Low-cost Solutions for Multilayer Nets East Exhibition Hall B + C #165
Leader Stochastic Gradient Descent for Distributed Training of Deep Learning Models East Exhibition Hall B + C #166
Learning Neural Networks with Adaptive Regularization East Exhibition Hall B + C #167
Memory Efficient Adaptive Optimization East Exhibition Hall B + C #168
On the Convergence Rate of Training Recurrent Neural Networks East Exhibition Hall B + C #169
SGD on Neural Networks Learns Functions of Increasing Complexity East Exhibition Hall B + C #170
Towards Understanding the Importance of Shortcut Connections in Residual Networks East Exhibition Hall B + C #171
Trivializations for Gradient-Based Optimization on Manifolds East Exhibition Hall B + C #172
Using Statistics to Automate Stochastic Optimization East Exhibition Hall B + C #173
Which Algorithmic Choices Matter at Which Batch Sizes? Insights From a Noisy Quadratic Model East Exhibition Hall B + C #174
Wide Neural Networks of Any Depth Evolve as Linear Models Under Gradient Descent East Exhibition Hall B + C #175
05:00 PM (Posters)
Algorithm-Dependent Generalization Bounds for Overparameterized Deep Residual Networks East Exhibition Hall B + C #195
Are deep ResNets provably better than linear predictors? East Exhibition Hall B + C #196
Efficient Rematerialization for Deep Networks East Exhibition Hall B + C #197
Fast Convergence of Natural Gradient Descent for Over-Parameterized Neural Networks East Exhibition Hall B + C #198
How to Initialize your Network? Robust Initialization for WeightNorm & ResNets East Exhibition Hall B + C #199
Lookahead Optimizer: k steps forward, 1 step back East Exhibition Hall B + C #200
Global Convergence of Gradient Descent for Deep Linear Residual Networks East Exhibition Hall B + C #201
Piecewise Strong Convexity of Neural Networks East Exhibition Hall B + C #202
PowerSGD: Practical Low-Rank Gradient Compression for Distributed Optimization East Exhibition Hall B + C #203
A Primal Dual Formulation For Deep Learning With Constraints East Exhibition Hall B + C #204
Surfing: Iterative Optimization Over Incrementally Trained Deep Networks East Exhibition Hall B + C #205
Theoretical Limits of Pipeline Parallel Optimization and Application to Distributed Deep Learning East Exhibition Hall B + C #206