Yuting Wei

Assistant Professor of Statistics and Data Science

Contact Information

Primary Email:
ytwei@wharton.upenn.edu

office Address:
307 Academic Research Building
265 South 37th Street
Philadelphia, PA 19104

Research Interests: high-dimensional and nonparametric statistics, statistical inference, reinforcement learning, statistical genetics

Links: Personal Website

Overview

Education

Ph.D. in Statistics, University of California at Berkeley, 2018
Advisors: Martin Wainwright, Aditya Guntuboyina

B.S. in Statistics, Peking University, 2013

B.A. in Economics, Peking University, 2013

Academic Positions Held

Assistant Professor, Department of Statistics and Data Science,
the Wharton School, University of Pennsylvania, 2021-present

Assistant Professor, Department of Statistics and Data Science,
Carnegie Mellon University, 2019-2021

Stein’s Fellow / Lecturer, Statistics Department,
Stanford University, 2018-2019

Research

Pratik Patil, Arun Kumar Kuchibhotla, Yuting Wei, Alessandro Rinaldo (Under Revision), Mitigating multiple descents: A model-agnostic framework for risk monotonization.
Gen Li, Wei Fan, Yuting Wei (Under Revision), Approximate message passing from random initialization with applications to Z2 synchronization.
Gen Li and Yuting Wei (Under Revision), A non-asymptotic framework for approximate message passing in spiked models.
Gen Li, Yuejie Chi, Yuting Wei, Yuxin Chen, Minimax-Optimal Multi-Agent RL in Zero-Sum Markov Games With a Generative Model.
Gen Li, Laixi Shi, Yuxin Chen, Yuejie Chi, Yuting Wei (Under Review), Settling the Sample Complexity of Model-Based Offline Reinforcement Learning.
Shicong Cen, Chen Cheng, Yuxin Chen, Yuting Wei, Yuejie Chi (2022), Fast global convergence of natural policy gradient methods with entropy regularization, Operations Research, 7 (4), pp. 2563-2578.
Laixi Shi, Gen Li, Yuting Wei, Yuxin Chen, Yuejie Chi (2022), Pessimistic Q-Learning for Offline Reinforcement Learning: Towards Optimal Sample Complexity, International Conference on Machine Learning (ICML).
Gen Li, Yuting Wei, Yuejie Chi, Yuantao Gu, Yuxin Chen (2022), Sample complexity of asynchronous Q-learning: sharper analysis and variance reduction, IEEE Transactions on Information Theory, 68 (1), pp. 448-473.
Abstract: Gen
Yue Li and Yuting Wei (Under Review), Minimum L1 interpolators: Precise asymptotics and multiple descent.
Gen Li, Yuxin Chen, Yuejie Chi, Yuantao Gu, Yuting Wei (2021), Sample-Efficient Reinforcement Learning Is Feasible for Linearly Realizable MDPs with Limited Revisiting, Neural Information Processing Systems (NeurIPS).

Teaching

All Courses

MATH4990 - Supervised Study
Study under the direction of a faculty member. Intended for a limited number ofmathematics majors.
STAT4300 - Probability
Discrete and continuous sample spaces and probability; random variables, distributions, independence; expectation and generating functions; Markov chains and recurrence theory.
STAT9910 - Sem in Adv Appl of Stat
This seminar will be taken by doctoral candidates after the completion of most of their coursework. Topics vary from year to year and are chosen from advance probability, statistical inference, robust methods, and decision theory with principal emphasis on applications.
STAT9950 - Dissertation
Dissertation

Activity

Latest Research

Pratik Patil, Arun Kumar Kuchibhotla, Yuting Wei, Alessandro Rinaldo (Under Revision), Mitigating multiple descents: A model-agnostic framework for risk monotonization.

All Research

Yuting Wei

Contact Information

Overview

Education

Academic Positions Held

Research

Teaching

All Courses

MATH4990 - Supervised Study

STAT4300 - Probability

STAT9910 - Sem in Adv Appl of Stat

STAT9950 - Dissertation

Awards and Honors

Activity

Latest Research