INFORMS Annual Meeting (INFORMS, October 2023, Phoenix)
- Stochastic First-order Optimization for Robust Markov Decision Process (Tentative)
- Host: Sajad Khodadadian
Slides
Modeling and Optimization: Theory and Applications (MOPTA, August 2023, Lehigh)
- Stochastic First-order Optimization for Robust Markov Decision Process (Tentative)
- Host: Caleb Ju
Slides
SIAM Conference on Optimization (OP23, June 2023, Seattle)
- Policy Mirror Descent Inherectly Explores Action Space
- Host: Prof. Zhaoran Wang (Northwestern University), Prof. George Lan (Georgia Tech)
Slides
ISyE PhD Student Seminar (GaTech, April 2023, Atlanta)
- Policy Mirror Descent Inherectly Explores Action Space
- Student host: Xinyu Liu, Sourabh Choudhary
Slides
INFORMS Annual Meeting (INFORMS, October 2022, Indianapolis)
- Homotopic Policy Mirror Descent: Policy Convergence, Implicit Regularization, and Improved Sample Complexity
- Host: Prof. Afrooz Jalilzadeh (University of Arizona)
Slides
International Conference on Continuous Optimization (ICCOPT, July 2022, Lehigh University)
- Homotopic Policy Mirror Descent: Policy Convergence, Implicit Regularization, and Improved Sample Complexity
- Host: Prof. Ashwin Pananjady (Georgia Tech)
Slides
Annual Conference on Information Sciences and Systems (CISS, March 2022, Online)
- Block Policy Mirror Descent
- Host: Prof. Yuejie Chi (CMU)
Slides
Guest Lecture, ISyE 8813 (GaTech, December 2021, Atlanta)
- On Implicit Bias of Optimization Algorithms: A New Era of Interpolation
- Host: Prof. Tuo Zhao (GaTech)
Slides
Meta Ads Ranking Team (Meta, August 2021, Online)
- Adversarial training — Some Simple Theories and Applications
- Host: Dr. Xiaohan Wei (Meta)
Slides
Machine Learning PhD Student Seminar (GaTech, December 2020, Online)
- Adversarial training — Some Simple Theories and Applications
- Host: Benjamin Wilson, Enpeng Yuan
Slides
Bytedance AML Team (Seattle, June 2020, Online)
- Adversarial training — Some Simple Theories and Applications
- Host: Dr. Chong Wang (Bytedance, Now at Apple)
Slides