<Yi Tian>

I am a Research Scientist at Meta, on the Monetization GenAI team. I received my Ph.D. in EECS from MIT, advised by Prof. Suvrit Sra, with a minor in mathematics. During my Ph.D., I was fortunate to also work with Prof. Russ Tedrake and Prof. Kaiqing Zhang. I received my B.E. in Automation from Tsinghua University, where I was fortunate to be advised by Prof. Jiwen Lu and Prof. Keyou You. My research interests lie broadly in generative AI, reinforcement learning/control, robotics, optimization, game theory, and their intersections.

Google Scholar LinkedIn CV (ver: Apr 2024)

Research

Toward Understanding State Representation Learning in MuZero: A Case Study in Linear Quadratic Gaussian Control
Yi Tian, Kaiqing Zhang, Russ Tedrake, Suvrit Sra
62nd IEEE Conference on Decision and Control (CDC), 2023. [short] [long]

Convex and Non-Convex Optimization under Generalized Smoothness
Haochuan Li*, Jian Qian*, Yi Tian, Alexander Rakhlin, Ali Jadbabaie
37th Conference on Neural Information Processing Systems (NeurIPS), 2023. (Spotlight) [arXiv]

Can Direct Latent Model Learning Solve Linear Quadratic Gaussian Control?
Yi Tian, Kaiqing Zhang, Russ Tedrake, Suvrit Sra
5th Annual Learning for Dynamics & Control Conference (L4DC), 2023. (Oral) [arXiv]

Byzantine-Robust Federated Linear Bandits
Ali Jadbabaie, Haochuan Li, Jian Qian, Yi Tian
61st IEEE Conference on Decision and Control (CDC), 2022. [short] [long]

Complexity Lower Bounds for Nonconvex-Strongly-Concave Min-Max Optimization
Haochuan Li, Yi Tian, Jingzhao Zhang, Ali Jadbabaie
35th Conference on Neural Information Processing Systems (NeurIPS), 2021. [pdf] [arXiv]

Provably Efficient Algorithms for Multi-Objective Competitive RL
Tiancheng Yu, Yi Tian, Jingzhao Zhang, Suvrit Sra.
38th International Conference on Machine Learning (ICML), 2021. (Long talk) [pdf] [arXiv]

Online Learning in Unknown Markov Games
Yi Tian*, Yuanhao Wang*, Tiancheng Yu*, Suvrit Sra.
38th International Conference on Machine Learning (ICML), 2021. [pdf] [arXiv]

Towards Minimax Optimal Reinforcement Learning in Factored Markov Decision Processes
Yi Tian*, Jian Qian*, Suvrit Sra.
34th Conference on Neural Information Processing Systems (NeurIPS), 2020. (Spotlight) [pdf] [arXiv]

Towards Understanding the Trade-off Between Accuracy and Adversarial Robustness
Congyue Deng*, Yi Tian*.
International Conference on Machine Learning Workshop on Security and Privacy (ICMLW), 2019. [pdf]

Deep Progressive Reinforcement Learning for Skeleton-Based Action Recognition
Yansong Tang*, Yi Tian*, Peiyang Li, Jiwen Lu, Jie Zhou.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018. [pdf]

Action Recognition in RGB-D Egocentric Videos
Yansong Tang, Yi Tian, Jiwen Lu, Jianjiang Feng, Jie Zhou.
IEEE International Conference on Image Processing (ICIP), 2017. [pdf]