J. Kim, S. Min. Risk-sensitive Policy Optimization via Predictive CVaR Policy Gradient. Submitted to ICML 2024 (review ratings: 6/6/7/7)

S. Min, D. J. Russo. An Information-Theoretic Analysis of Nonstationary Bandit Learning. Submitted to Operations Research.

• Preliminary version: S. Min, D. J. Russo. An Information-Theoretic Analysis of Nonstationary Bandit Learning. Proceedings of the 40th International Conference on Machine Learning (ICML), PMLR 202:24831-24849, 2023

S. Min, C. Maglaras, C. C. Moallemi. Cross-sectional Variation of Intraday Liquidity, Cross-Impact, and their Effect on Portfolio Execution. Operations Research 70(2):830–846. March 2022

S. Min, C. Maglaras, C. C. Moallemi. Thompson Sampling with Information Relaxation Penalties. Accepted at Management Science.

• Preliminary version: S. Min, C. Maglaras, C. C. Moallemi. Thompson Sampling with Information Relaxation Penalties. In Advances in Neural Information Processing Systems 32, pages 3549–3558, 2019

Y. Kanoria, S. Min, P. Qian. The Competition for Partners in Matching Markets. Accepted at Management Science.

• Preliminary version: Y. Kanoria, S. Min, P. Qian. In Which Matching Markets does the Short Side Enjoy an Advantage? Proceedings of the Thirty-Second Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), pages 1374–1386, March 2021

S. Min, C. Maglaras, C. C. Moallemi. Risk-sensitive Optimal Execution via a Conditional Value-at-Risk Objective. Major revision at Management Science. Initial version: Nov 2020. 2021 INFORMS Section on Finance Best Student Paper Competition Finalist.

S. Min, C. C. Moallemi, D. J. Russo. Policy Gradient Optimization of Thompson Sampling Policies. Submitted to INFORMS Journal on Computing. Initial version: June 2020.