See How Your Research Aligns
Create a free account to analyze your research alignment,
identify potential research gaps, and generate personalized
application documents for this professor.
Create Free Account
Tengyu Ma
Deep Learning Theory
Non-convex Optimization
Reinforcement Learning
Representation Learning
Distributed Optimization
About
Tengyu Ma is an Assistant Professor of Computer Science at Stanford University. His research focuses on machine learning and algorithms, especially topics such as deep learning theory, non‑convex optimization, reinforcement learning, representation learning, distributed optimization, and high‑dimensional statistics.
He received his Ph.D. from Princeton University and his undergraduate degree from Tsinghua University. Ma has been recognized with several honors, including a Sloan Research Fellowship, an NSF CAREER Award, and an ACM Doctoral Dissertation Award Honorable Mention.
Research Performance Summary
2011-2026
Active Research Span
First Recorded Paper
A new variation of hat guessing games
Year:
2011
Citations:
9
Venue:
International Computing and Combinatorics Conference
Latest Recorded Paper
Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning
Year:
2026
Citations:
0
Venue:
arXiv preprint arXiv:2601.23027
Last 10 Years Publication Activity
This timeline shows the professor's yearly publication activity.
Publication Venues and Collaboration
Journal, Conference, and Book Publication Breakdown
Top Coauthors
Liang
Wei
Arora
Research Impact by Period
Papers
6
Citations
79
Avg. Citations / Paper
13.2
H-Index
3
Papers
76
Citations
21045
Avg. Citations / Paper
276.9
H-Index
52
Papers
40
Citations
13656
Avg. Citations / Paper
341.4
H-Index
36
Papers
5
Citations
653
Avg. Citations / Paper
130.6
H-Index
4
Contact and Professional Links
Detected Research Keywords
Opportunities Risks Foundation
Risks Foundation Models
Residual Learning Without
Learning Without Normalization
Provable Guarantees Supervised
Guarantees Supervised Learning
Supervised Learning Spectral
Learning Spectral Contrastive
Spectral Contrastive Loss
Document Level Relation