Dissertation
Book Chapter
Journal Papers
Power-of-2-Arms for Adversarial Bandit Learning with Switching Costs
Ming Shi, Xiaojun Lin, and Lei Jiao
IEEE/ACM Transactions on Networking, December 2024, DOI: 10.1109/TON.2024.3522073. [IEEE/ACM ToN]
Competitive Online Convex Optimization with Switching Costs and Ramp Constraints
Ming Shi, Xiaojun Lin, and Sonia Fahmy
IEEE/ACM Transactions on Networking, vol. 29, no. 2, pp. 876-889, April 2021, DOI: 10.1109/TNET.2021.3053910. [IEEE/ACM ToN]
Combining Regularization With Look-Ahead for Competitive Online Convex Optimization
Ming Shi, Xiaojun Lin, and Lei Jiao
IEEE/ACM Transactions on Networking, vol. 32, no. 3, pp. 2391-2405, June 2024, DOI: 10.1109/TNET.2024.3350990. [IEEE/ACM ToN]
Conference Papers
Designing Near-Optimal Partially Observable Reinforcement Learning
Ming Shi, Yingbin Liang, and Ness Shroff
IEEE Military Communications Conference (IEEE MILCOM), Washington, DC, USA, October 2024.
Theoretical Hardness and Tractability of POMDPs in RL with Partial Online State Information
Ming Shi, Yingbin Liang, and Ness Shroff
preprint on arXiv, 2023.
A Near-Optimal Algorithm for Safe Reinforcement Learning Under Instantaneous Hard Constraints
Ming Shi, Yingbin Liang, and Ness Shroff
40th International Conference on Machine Learning (ICML), Hawaii, USA, July 2023.
Near-Optimal Adversarial Reinforcement Learning with Switching Costs
Ming Shi, Yingbin Liang, and Ness Shroff
11th International Conference on Learning Representations (ICLR), Kigali, Rwanda, May 2023. (Spotlight, with acceptance rate 8.0%.)
Leveraging Synergies Between AI and Networking to Build Next Generation Edge Networks
Ming Shi, Sen Lin (co-first author), Yingbin Liang, Ness Shroff, et al.
8th IEEE International Conference on Collaboration and Internet Computing (IEEE CIC), virtual conference, December 2022.
Power-of-2-Arms for Bandit Learning with Switching Costs
Ming Shi, Xiaojun Lin, and Lei Jiao
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%.)
Combining Regularization with Look-Ahead for Competitive Online Convex Optimization
Ming Shi, Xiaojun Lin, and Lei Jiao
IEEE Conference on Computer Communications (IEEE INFOCOM), virtual conference, May 2021. (Acceptance rate: 19.9%.)
Competitive Online Convex Optimization with Switching Costs and Ramp Constraints
Ming Shi, Xiaojun Lin, Sonia Fahmy, and DongHoon Shin
IEEE Conference on Computer Communications (IEEE INFOCOM), Honolulu, Hawaii, USA, April 2018. (Acceptance rate: 19.2%.)
Working Papers
Joint Reward Maximization and Safety Guarantee for Reinforcement Learning with Human-in-the-Loop
Ming Shi, Yingbin Liang, Ness Shroff, and Ananthram Swami, manuscript in preparation.
Multi-Agent Reinforcement Learning for Autonomous Networked Systems with Switching Costs
Ming Shi, and Adam Wierman, preparing.
On the Value of Uncertain Human Feedback in Reinforcement Learning with Non-Stationary Reward
Ming Shi, Yingbin Liang, and Ness Shroff, manuscript in preparation.
𝑉-Learning for Provably Efficient Reinforcement Learning in Partially Observable Biomedical Markov Games
Ming Shi, Yingbin Liang, and Ness Shroff, manuscript in preparation.
Technical Reports
|