Yichen Chen

I am a fifth-year graduate student in the Department of Computer Science at Princeton University. My advisor is Professor Mengdi Wang.

I am broadly interested in Stochastic Optimization. Particularly, I am interested in developing efficient algorithms for Reinforcement Learning from the perspective of optimization. Before joining Princeton University, I received my BS degree in computer science from Shanghai Jiao Tong University in 2014.

Papers

Scalable Bilinear Pi Learning Using State and Action Features
Yichen Chen, Lihong Li, Mengdi Wang
International Conference on Machine Learning (ICML), 2018
[Link]
Hardness of Approximation for A Class of Sparse Optimization Problems
Yichen Chen, Yinyu Ye, Mengdi Wang
Journal of Machine Learning Research (JMLR), 2018
Strong NP-Hardness for Sparse Optimization with Concave Penalty Functions
Yichen Chen, Dongdong Ge, Mengdi Wang, Zizhuo Wang, Yinyu Ye, Hao Yin
International Conference on Machine Learning (ICML), 2017
[Link]
Online Value-Policy Iteration for Discounted Markov Decision Process
Mengdi Wang, Yichen Chen
Conference of Decision and Control (CDC), 2016
[Link]
Random Multi-Constraint Projection: Stochastic Gradient Methods for Convex Optimization with Many Constraints
Mengdi Wang, Yichen Chen
In revision with Mathematics of Operations Research
[Arxiv]
Stochastic Primal-Dual Methods and Sample Complexity of Reinforcement Learning
Yichen Chen, Mengdi Wang
In revision with Journal of Machine Learning Research (JMLR)
[Arxiv]
Lower Bound On the Computational Complexity of Discounted Markov Decision Problems
Yichen Chen, Mengdi Wang
Submitted, 2017
[Arxiv]
Sparse Principal Component Analysis in Frequency Domain for Time Series
Junwei Lu, Yichen Chen, Xiuneng Zhu, Fang Han, Han Liu
Submitted, 2015
[Link]

Awards