Research
Research Papers
- Large Scale Markov Decision Processes with Adversarial Rewards. With He Wang, and Huan Xu. Accepted at Neural Information Processing Systems (NeurIPS), 2019. [arxiv, slides]
- Competing Against Equilibria in Zero-Sum Games with Evolving Payoffs. With Jacob Abernethy, He Wang, and Huan Xu. In Proceedings of the International Conference on Machine Learning (ICML), 2019. [paper] [arxiv, with experiments]
- The Online Saddle Point Problem: Applications to Constrained Online Convex Optimization. With He Wang and Huan Xu. Submitted to Mathematics of Operations Research. [arxiv]
- Risk-Averse Stochastic Convex Bandit. With Huan Xu. In Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), 2019. [paper, arxiv]
- Differentially Private Online Submodular Minimization. With Rachel Cummings. In Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics (AISTATS), 2019. [paper]
Talks
- Competing Against Equilibria in Zero-Sum Games with Evolving Payoffs, ICML, Long Beach, CA, June 2019
- Risk-Averse Stochastic Convex Bandit, AISTATS, Okinawa, Japan Apr, 2019
- Differentially Private Online Submodular Minimization, AISTATS, Okinawa, Japan Apr, 2019
- A Quick Tutorial on Online Learning, Georgia Tech. Sept, 2018
- Differentially Private Online Submodular Minimization, Georgia Tech. Dec, 2017
- Two-Stage Stochastic Programs with Hard Second-Stage Problems, Georgia Tech. May, 2017
- Tutorial on Robust Optimization, Georgia Tech. May 2017