Poster
|
Thu 10:45
|
Practical Two-Step Lookahead Bayesian Optimization
Jian Wu · Peter Frazier
|
|
Poster
|
Tue 10:45
|
Stagewise Training Accelerates Convergence of Testing Error Over SGD
Zhuoning Yuan · Yan Yan · Rong Jin · Tianbao Yang
|
|
Poster
|
Wed 10:45
|
A Stochastic Composite Gradient Method with Incremental Variance Reduction
Junyu Zhang · Lin Xiao
|
|
Poster
|
Thu 10:45
|
First-order methods almost always avoid saddle points: The case of vanishing step-sizes
Ioannis Panageas · Georgios Piliouras · Xiao Wang
|
|
Poster
|
Thu 17:00
|
Are deep ResNets provably better than linear predictors?
Chulhee Yun · Suvrit Sra · Ali Jadbabaie
|
|
Poster
|
Wed 17:00
|
Möbius Transformation for Fast Inner Product Search on Graph
Zhixin Zhou · Shulong Tan · Zhaozhuo Xu · Ping Li
|
|
Poster
|
Wed 17:00
|
Accelerating Rescaled Gradient Descent: Fast Optimization of Smooth Functions
Ashia Wilson · Lester Mackey · Andre Wibisono
|
|
Poster
|
Thu 10:45
|
Local SGD with Periodic Averaging: Tighter Analysis and Adaptive Synchronization
Farzin Haddadpour · Mohammad Mahdi Kamani · Mehrdad Mahdavi · Viveck Cadambe
|
|
Poster
|
Thu 17:00
|
Piecewise Strong Convexity of Neural Networks
Tristan Milne
|
|
Poster
|
Thu 10:45
|
Imitation-Projected Programmatic Reinforcement Learning
Abhinav Verma · Hoang Le · Yisong Yue · Swarat Chaudhuri
|
|
Poster
|
Thu 10:45
|
Trivializations for Gradient-Based Optimization on Manifolds
Mario Lezcano Casado
|
|
Poster
|
Tue 10:45
|
An Improved Analysis of Training Over-parameterized Deep Neural Networks
Difan Zou · Quanquan Gu
|
|