• Selected Papers

1. Journal:

Ming Shi, Xiaojun Lin and Sonia Fahmy, “Competitive Online Convex Optimization With Switching Costs and Ramp Constraints,” in IEEE/ACM Transactions on Networking, vol. 29, no. 2, pp. 876-889, April 2021, DOI: 10.1109/TNET.2021.3053910.

Ming Shi, Xiaojun Lin and Lei Jiao, “Power-of-2-Arms for Adversarial Bandit Learning With Switching Costs,” minor revision, IEEE/ACM Transactions on Networking, May 2023.

Ming Shi, Xiaojun Lin and Lei Jiao, “Combining Regularization With Look-Ahead for Competitive Online Convex Optimization,” in IEEE/ACM Transactions on Networking, vol. 32, no. 3, pp. 2391-2405, June 2024, DOI: 10.1109/TNET.2024.3350990.

2. Conference:

Ming Shi, Yingbin Liang, and Ness Shroff, "Designing Near-Optimal Partially Observable Reinforcement Learning," in IEEE Military Communications Conference (IEEE MILCOM), Washington, DC, USA, October 2024.

Ming Shi, Yingbin Liang, and Ness Shroff, "A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints," in 40th International Conference on Machine Learning (ICML), Hawaii, USA, July 2023.

Ming Shi, Yingbin Liang, and Ness Shroff, "Near-Optimal Adversarial Reinforcement Learning with Switching Costs," in 11th International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 2023. (Spotlight, with acceptance rate 8.0%.)

Ming Shi, Xiaojun Lin and Lei Jiao, “Power-of-2-Arms for Bandit Learning with Switching Costs,” in 23rd International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing (ACM MobiHoc), Seoul, South Korea, October 2022. (Acceptance rate: 19.8%.)

Ming Shi, Xiaojun Lin and Lei Jiao, “Combining Regularization with Look-Ahead for Competitive Online Convex Optimization,” in IEEE Conference on Computer Communications (IEEE INFOCOM), virtual conference, May 2021. (Acceptance rate: 19.9%.)

Ming Shi, Xiaojun Lin, Sonia Fahmy, and DongHoon Shin, “Competitive Online Convex Optimization with Switching Costs and Ramp Constraints,” in IEEE Conference on Computer Communications (IEEE INFOCOM), Honolulu, Hawaii, USA, April 2018. (Acceptance rate: 19.2%.)

3. Book Chapter:

Ming Shi, Yingbin Liang, and Ness B. Shroff, "Adversarial Online Reinforcement Learning Under Limited Defender Resources", in Network Security Empowered by Artificial Intelligence, Springer, Series ISSN 1568-2633, June 2024.