Zeyu Jia

Zeyu Jia

Massachusetts Institute of Technology

H-index: 5

North America-United States

About Zeyu Jia

Zeyu Jia, With an exceptional h-index of 5 and a recent h-index of 5 (since 2020), a distinguished researcher at Massachusetts Institute of Technology, specializes in the field of optimization, statistics.

His recent articles reflect a diverse array of research interests and contributions to the field:

Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data

When is Agnostic Reinforcement Learning Statistically Tractable?

Entropic characterization of optimal rates for learning Gaussian mixtures

Linear reinforcement learning with ball structure action space

Rate of convergence of the smoothed empirical Wasserstein distance

Non-parametric threshold for smoothed empirical Wasserstein distance

Intrinsic dimension estimation using Wasserstein distances

Search direction correction with normalized gradient makes first-order methods faster

Zeyu Jia Information

University

Position

___

Citations(all)

544

Citations(since 2020)

544

Cited By

87

hIndex(all)

5

hIndex(since 2020)

5

i10Index(all)

4

i10Index(since 2020)

4

Email

University Profile Page

Google Scholar

Zeyu Jia Skills & Research Interests

optimization

statistics

Top articles of Zeyu Jia

Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data

arXiv preprint arXiv:2403.17091

2024/3/25

When is Agnostic Reinforcement Learning Statistically Tractable?

Advances in Neural Information Processing Systems

2024/2/13

Entropic characterization of optimal rates for learning Gaussian mixtures

2023/7/12

Zeyu Jia
Zeyu Jia

H-Index: 4

Yihong Wu
Yihong Wu

H-Index: 26

Linear reinforcement learning with ball structure action space

2023/2/13

Zeyu Jia
Zeyu Jia

H-Index: 4

Rate of convergence of the smoothed empirical Wasserstein distance

arXiv preprint arXiv:2205.02128

2022/5/4

Non-parametric threshold for smoothed empirical Wasserstein distance

2022

Zeyu Jia
Zeyu Jia

H-Index: 4

Intrinsic dimension estimation using Wasserstein distances

arXiv preprint arXiv:2106.04018

2021/6/8

Search direction correction with normalized gradient makes first-order methods faster

SIAM Journal on Scientific Computing

2021

Minimax-optimal off-policy evaluation with linear function approximation

2020/11/21

Model-based reinforcement learning with value-targeted regression

2020/11/21

Towards solving 2-TBSG efficiently

Optimization Methods and Software

2020/7/3

See List of Professors in Zeyu Jia University(Massachusetts Institute of Technology)

Co-Authors

academic-engine