Skip to content
conftrace_
2021 COLT COLT 2021

Open Problem: Can Single-Shuffle SGD be Better than Reshuffling SGD and GD?

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built. Papers without an abstract are not sent to the classifier, which is why this one carries no topics.

❓ The Questioner

Authors

Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Download PDF

More from COLT 2021

All COLT 2021 papers →
Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation
Improved Algorithms for Efficient Active Learning Halfspaces with Massart and Tsybakov Noise
Is Reinforcement Learning More Difficult Than Bandits? A Near-optimal Algorithm Escaping the Curse of Horizon
Nearly Minimax Optimal Reinforcement Learning for Linear Mixture Markov Decision Processes
A Local Convergence Theory for Mildly Over-Parameterized Two-Layer Neural Network
Benign Overfitting of Constant-Stepsize SGD for Linear Regression