226 citations · 1.9k across the 128 of their papers we have counts for
6 papers · 2 filters
Learning Adversarial MDPs with Bandit Feedback and Unknown Transition
Chi Jin, Tiancheng Jin, Haipeng Luo +2
We consider the problem of learning in episodic finite-horizon Markov decision processes with an unknown transition function, bandit feedback, and adversarial losses. We propose an…
Efficient Policy Learning for Non-Stationary MDPs under Adversarial Manipulation
Tiancheng Yu, Suvrit Sra
A Markov Decision Process (MDP) is a popular model for reinforcement learning. However, its commonly used assumption of stationary dynamics and rewards is too stringent and fails t…
Near Optimal Stratified Sampling
Tiancheng Yu, Xiyu Zhai, Suvrit Sra
The performance of a machine learning system is usually evaluated by using i.i.d.\ observations with true labels. However, acquiring ground truth labels is expensive, while obtaini…
Are deep ResNets provably better than linear predictors?
Chulhee Yun, Suvrit Sra, Ali Jadbabaie
Recent results in the literature indicate that a residual network (ResNet) composed of a single residual block outperforms linear predictors, in the sense that all local minima in…
Flexible Modeling of Diversity with Strongly Log-Concave Distributions
Joshua Robinson, Suvrit Sra, Stefanie Jegelka
Strongly log-concave (SLC) distributions are a rich class of discrete probability distributions over subsets of some ground set. They are strictly more general than strongly Raylei…
Escaping Saddle Points with Adaptive Gradient Methods
Matthew Staib, Sashank J. Reddi, Satyen Kale +2
Adaptive methods such as Adam and RMSProp are widely used in deep learning but are not well understood. In this paper, we seek a crisp, clean and precise characterization of their…