Chicheng Zhang

Revisiting Perceptron: Efficient and Label-Optimal Learning of Halfspaces

2017 · arXiv (Cornell University)

It has been a long-standing problem to efficiently learn a halfspace using as few labels as possible in the presence of noise. In this work, we propose an efficient Perceptron-based algorithm for actively learning homogeneous …

Provably Efficient Multi-Task Reinforcement Learning with Model Transfer

2021 · arXiv (Cornell University)

We study multi-task reinforcement learning (RL) in tabular episodic Markov decision processes (MDPs). We formulate a heterogeneous multi-player RL problem, in which a group of players concurrently face similar but not necessarily identical MDPs, with …