Qingsong Liu | Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University

About Me

I am a Ph.D. student at Institute for Interdisciplinary Information Sciences (IIIS), Tsinghua University, supervised by Prof. Zhixuan Fang. I achieved my Bachelor’s degree at Department of Electronic Engineering of Tsinghua University. Previsouly, I worked with Prof. Wenfei Wu.

Research Interests

Constrained Online Learning, Multi-agent Online Learning
Online Learning in Computer Systems and Communication Networks

Selected Conference Papers

Learning the Optimal Control for Evolving Systems with Converging Dynamics
Qingsong Liu and Zhixuan Fang
54th ACM SIGMETRICS conference. Sigmetrics 2024.
Decentralized Scheduling with QoS Constraints: Achieving O(1) QoS regret of Multi-player Bandits
Qingsong Liu and Zhixuan Fang
38th AAAI Conference on Artificial Intelligence. AAAI 2024.
Learning-based Scheduling for Information Gathering with QoS Constraints
Qingsong Liu, Weihang Xu, and Zhixuan Fang
37th IEEE International Conference on Computer Communications. INFOCOM 2024.
Adversarial Combinatorial Bandits with Switching Cost and Arm Selection Constraints
Yin Huang (co-primary), Qingsong Liu (co-primary), and Jie Xu
37th IEEE International Conference on Computer Communications. INFOCOM 2024.
Learning to Schedule Tasks with Deadline and Throughput Constraints
Qingsong Liu and Zhixuan Fang
36th IEEE International Conference on Computer Communications. INFOCOM 2023.
Combinatorial Bandits with Linear Constraints: Beyond Knapsacks and Fairness
Qingsong Liu, Weihang Xu, Siwei Wang, and Zhixuan Fang
36th Annual Conference on Neural Information Processing Systems. NeurIPS 2022.
Online Convex Optimization with Switching Costs: Algorithms and Performance
Qingsong Liu, Zhuoran Li, and Zhixuan Fang
20th International Symposium on Modeling and Optimization in Mobile, Ad Hoc and Wireless Networks. WiOpt 2022.
Simultaneously Achieving Sublinear Regret and Constraint Violations for Online Convex Optimization with Time-varying Constraints
Qingsong Liu, Wenfei Wu, Longbo Huang, and Zhixuan Fang
39th International Symposium on Computer Performance, Modeling, Measurements and Evaluation. Performance 2021.

Journal Papers

The Optimal Dynamic Regret for Smoothed Online Convex Optimization with Squared l2 Norm Switching Cost
Yaoyu Zhang (co-primary), Qingsong Liu (co-primary), Jian Sun, and Chenye Wu
Journal of the Franklin Institute, 2023 (Part of this work is presented in American Control Conference 2022).
Simultaneously Achieving Sublinear Regret and Constraint Violations for Online Convex Optimization with Time-varying Constraints
Qingsong Liu, Wenfei Wu, Longbo Huang, and Zhixuan Fang
Elsevier’s Performance Evaluation (PEVA), volume 152, 2021.

Services

Conference Reviewers: AISTATS 2023, and CDC 2022.
Journal Reviewers: TMC, and TNNLS.

Teaching