معرفی
Chi Jin is an Assistant Professor of Electrical and Computer Engineering at Princeton University's School of Engineering and Applied Science. His research focuses on theoretical foundations of machine learning with emphasis on reinforcement learning, nonconvex optimization, and algorithmic game theory.
Educational background:
- Ph.D. in Electrical Engineering and Computer Sciences, University of California, Berkeley (2019)
- B.Sc. in Physics, Peking University (2012)
His research addresses fundamental challenges in nonconvex optimization and minimax problems, developing provably efficient algorithms for complex learning scenarios. Key contributions include establishing theoretical guarantees for escaping saddle points, efficient Q-learning convergence, and principled approaches to out-of-distribution generalization. Recent work increasingly integrates formal methods with large language models for theorem proving and multi-agent economic simulation.
Notable scientific awards:
- Best Paper at ICML 2018 workshop 'Exploration in RL'
- Sloan Research Fellowship
- SEAS Junior Faculty Award
As an advisor, he mentors graduate students across departments including ORFE, COS, and PLI. His research group develops theoretically grounded algorithms with practical applications in secure communications, automated theorem proving, and multi-agent systems. Current projects explore the intersection of formal verification with generative AI, and principled approaches to multi-agent reinforcement learning in complex environments.
