Jianyi Yang

prof_pic.jpg
Contact. jyang71@Central.UH.EDU or jianyiyang.ai@gmail.com

I am an Assistant Professor in the Department of Computer Science at the University of Houston with a joint appointment in the Department of Electrical and Computer Engineering. Prior to that, I was a visitor at Caltech and a postdoctoral research assistant at UC Riverside, working with Prof. Adam Wierman and Prof. Shaolei Ren. I received my PhD degree in 2023 at UC Riverside, advised by Prof. Shaolei Ren.

My research interests span AI/ML algorithms and their applications in computing systems. My research seeks to advance trustworthy and efficient AI, building reliable, responsible, and efficient AI systems. My research methodologies include reinforcement learning, online learning/optimization, knowledge informed learning, learning-augmented algorithms, etc.

I am actively seeking self-motivated PhD students and research assistants starting Spring 2025 or Fall 2025. If you have an interest, please contact me and send me your CV and transcripts. Details in the link Openings.

news

Sep 25, 2024 Our paper Online Budgeted Matching with General Bids has been accepted by Neurips 2024! It provides a provable algorithm to solve online budgeted matching problem with general bids. Manuscript will come out soon.
Sep 25, 2024 Our paper Learning-Augmented Decentralized Online Convex Optimization in Networks has been accepted by Sigmetrics’25! It proposes a novel algorithm to provably robustify machine learning predictions for decentralized optimization in networks. Our first-author Pengfei Li is on the job market this year. Pengfei is an excellent researcher and a reliable collaborator. We have worked together on a lot of works. Please reach out to him if you have position information!
May 1, 2024 Our paper Building Socially-Equitable Public Models was accepted by ICML 2024! Congratulations to Yejia and other co-authors!
Feb 23, 2024 I attended ITA Workshop 2024 at San Diego and gave a talk named Online Budgeted Allocation: Worst Case Guarantee and Learning Augmentation (paper accepted by SIGMETRICS’24).
Dec 13, 2023 Our paper Online Allocation with Replenishable Budgets: Worst Case and Beyond was accepted by ACM SIGMETRICS 2024! Online resource allocation with replenishments is one of the key problems for carbon neutral and/or water self-sufficient computing and is important for network resource management, online advertising, etc. This paper provides fundamental algorithms with worst-case guarantees for this problem and proposes a learning-augmented algorithm to improve the statistical performance under worst-case guarantee.

selected publications

  1. SIGMETRICS
    Online Allocation with Replenishable Budgets: Worst Case and Beyond
    Jianyi Yang, Pengfei Li, Mohammad J. Islam, and Shaolei Ren
    ACM International Conference on Measurement and Modeling of Computer Systems, 2024
  2. NeurIPS
    Anytime-Competitive Reinforcement Learning with Policy Prior
    Jianyi Yang, Pengfei Li, Tongxin Li, Adam Wierman, and Shaolei Ren
    Neural Information Processing Systems, 2023
  3. NeurIPS
    Robust Learning for Smoothed Online Convex Optimization with Feedback Delay
    Pengfei Li, Jianyi Yang, Adam Wierman, and Shaolei Ren
    Neural Information Processing System, 2023
  4. ICML
    Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees
    Pengfei Li, Jianyi Yang, and Shaolei Ren
    International Conference on Machine Learning, 2023
  5. ICML
    Informed Learning by Wide Neural Networks: Convergence, Generalization and Sampling Complexity
    Jianyi Yang, and Shaolei Ren
    International Conference on Machine Learning, 2022
  6. SIGMETRICS
    Expert-Calibrated Learning for Online Optimization with Switching Costs
    Pengfei Li*, Jianyi Yang*, and Shaolei Ren
    ACM International Conference on Measurement and Modeling of Computer Systems, 2022
  7. SIGMETRICS
    One Proxy Device Is Enough for Hardware-Aware Neural Architecture Search
    Bingqian Lu, Jianyi Yang, Weiwen Jiang, Yiyu Shi, and Shaolei Ren
    ACM International Conference on Measurement and Modeling of Computer Systems, 2022