研究方向

在线学习与在线优化

在线学习和在线优化方法的基本思想是结合模型驱动（Model-based）和数据驱动（Data-driven）方法的长处，通过在线调节模型的决策策略，折衷保持算法的经验性能和理论性能。

多智能体在线强化学习

多智能体强化学习协调多个智能体在环境中进行交互学习，每个智能体在观察、测量环境的动态性的同时，协同其他智能体的行为，进行最优决策。

大模型加速推理与软硬件优化

大模型加速推理与软硬件优化致力于突破边缘端芯片的资源限制。其核心在于通过软硬件协同设计，从模型层、执行层、软硬件协同层三个维度，构建了大模型加速推理的全栈优化体系：模型侧通过稀疏化、量化等技术精简计算负载；推理执行侧通过智能调度策略提升资源利用率；软硬件结合侧则深度适配硬件特性，从计算精度、存储管理、多核调度等方面实现软硬协同，最终全方位突破大模型推理的性能瓶颈。

发表论文

Asynchronous Multi-Agent Bandits: Fully Distributed vs. Leader-Coordinated Algorithms
Xuchuang Wang, Janice Chen, Xutong Liu, Lin Yang*, Mohammad Hajiesmaili, John CS Lui, Don Towsley
ACM SIGMETRICS, June 2025 (Full Paper)
Near-Optimal Regret Bounds for Federated Multi-armed Bandits with Fully Distributed Communication
Haoran Zhang, Xuchuang Wang, Haoxu Chen, Hao Qiu, Lin Yang*, Yang Gao
UAI 2025 (Full Paper)
Combinatorial Ski Rental Problem:Robust and Learning-Augmented Algorithms
Ziwei Li, Bo Sun, Zhiqiu Zhang, Mohammad Hajiesmaili, Binghan Wu, Lin Yang*, Yang Gao
NeurIPS 2025 (Full Paper)
Federated Multi-armed Bandits with Efficient Bit-Level Communications
Haoran Zhang, Yang Xu, Xuchuang Wang, HaoXu Chen, Hao Qiu, Lin Yang*, Yang Gao
NeurIPS 2025 (Full Paper)
Distributed Multi-agent Bandits Over Erdős-Rényi Random Networks
Jingyuan Liu · Hao Qiu · Lin Yang · Mengfan Xu
NeurIPS 2025
VETA-DiT: Variance-Equalized and Temporally Adaptive Quantization for Efficient 4-bit Diffusion Transformers
Qinkai Xu · Yijin Liu · Yang Chen · Lin Yang · Li Li · Yuxiang Fu
NeurIPS 2025
Cooperative Multi-agent Bandits: Distributed Algorithms with Optimal Individual Regret and Communication Costs
Lin Yang, Xuchuang Wang, Mohammad Hajiesmaili, Lijun Zhang, John C.S. Lui, Don Towsley
Reinforcement Learning Conference 2024 (Full Paper)
Exploration for Free: How Does Reward Heterogeneity Improve Regret in Cooperative Multi-agent Bandits?
Xuchuang Wang, Lin Yang, Yu-Zhen Janice Chen, Xutong Liu, Mohammad Hajiesmaili, Don Towsley, John C.S. Lui
UAI 2023 (Full Paper)
On-Demand Communication for Asynchronous Multi-Agent Bandits
Yu-zhen Janice Chen, Lin Yang, Xuchuang Wang, Xutong Liu, Mohammad Hajiesmaili, John C.S. Lui, Don Towsley
AISTATS 2023
Achieve Near-Optimal Individual Regret & Low Communications in Multi-Agent Bandits
Xuchuang Wang, Lin Yang, Yu-zhen Janice Chen, Xutong Liu, Mohammad Hajiesmaili, Don Towsley, John C.S. Lui
ICLR 2023
The Online Knapsack Problem with Departures
Bo Sun#, Lin Yang#, Mohammad Hajiesmaili, Adam Wierman, Don Towsley
SIGMETRICS 2023 (Full Paper)
Hierarchical Learning Algorithms for Multi-scale Expert Problems
Lin Yang, Yu-zhen Chen, Mohammad Hajiesmaili, Mark Herbster, Don Towsley
SIGMETRICS 2022 (Full Paper); Journal Version: POMACS, 6(2), 1-29, 2022
Distributed Bandits with Heterogeneous Agents
Lin Yang, Yu-zhen Chen, Mohammad Hajiesmaili, John CS Lui, Don Towsley
INFOCOM 2022
Competitive Algorithms for Online Multidimensional Knapsack Problems
Lin Yang, Ali Zeynali, Mohammad Hajiesmaili, Ramesh Sitaraman, Donald F. Towsley
SIGMETRICS 2022 (Full Paper); Journal Version: POMACS, 5(3), 1-30, 2021
Cooperative Stochastic Bandits with Asynchronous Agents and Constrained Feedback
Lin Yang, Yu-Zhen Janice Chen, Stephen Pasteris, Mohammad Hajiesmaili, John CS Lui, Don Towsley
NeurIPS 2021
Competitive Bidding Strategies for Online Linear Optimization with Inventory Management Constraints
Russell Lee, Yutao Zhou, Lin Yang, Mohammad Hajiesmaili, Ramesh Sitaraman
Performance 2021
Learning Based Control Policy and Regret Analysis for Online Quadratic Optimization with Asymmetric Information Structure
Cheng Tan, Lin Yang, Wing Shing Wong
Transactions on Cybernetics, 2021
Adversarial Bandits with Corruptions: Regret Lower Bound and No-regret Algorithm
Lin Yang, Mohammad Hajiesmaili, Mohammad Sadegh Talebi, John CS Lui, Wing Shing Wong
NeurIPS 2020
Online Linear Optimization with Inventory Management Constraints
Lin Yang, Mohammad Hajiesmaili#, Ramesh Sitaraman, Adam Wierman, Enrique Mallada, Wing Shing Wong
SIGMETRICS 2020 (Full Paper); Journal Version: POMACS, 4(1), 1-29, 2020
Online Linear Programming with Uncertain Constraints
Lin Yang, Mohammad H. Hajiesmaili, Wing Shing Wong
CISS 2019 (Invited Paper)
Stabilization of Discrete Time Stochastic System with Input Delay and Control Dependent Noise
Cheng Tan, Lin Yang, Fangfang Zhang, Zhenqiang Zhang, Wing Shing Wong
Systems & Control Letters, 2019, 123: 62-68
An Average Queue-Length-Difference-Based Congestion Detection Algorithm in TCP/AQM Network
Jin Zhu, Tong Luo, Lin Yang, Wanqing Xie, G. E. Dullerud
International Journal of Adaptive Control and Signal Processing, 2018
Hour-Ahead Offering Strategies in Electricity Market for Power Producers with Storage and Intermittent Supply
Lin Yang, Mohammad H. Hajiesmaili#, Hanling Yi, Minghua Chen
SIGMETRICS 2017 (Poster Paper)
Gittins Index Based Control Policy for a Class of Pursuit-Evasion Problems
Cheng Tan, Changbao Xu, Lin Yang, Wing Shing Wong
IET Control Theory and Applications, 12(1), 110-118, 2017
Competitive Online Algorithms for Geographical Load Balancing in Data Centers with Energy Storage
Chi-Kin Chau, Lin Yang
EEDC Workshop 2016
An Optimal Vertical Handoff Decision Algorithm for Multiple Services with Different Priorities in Heterogeneous Wireless Networks
Jin Zhu, Limin Xu, Lin Yang, Wanqing Xie
Wireless Personal Communications 83 (1), 527-549, 2015
Time Series Analysis for Congestion Detection in TCP/AQM Networks
Lin Yang, Jin Zhu, Wanqing Xie, G. E. Dullerud
IEEE Communications Letters, 19(3), 331-334, 2015