Pengfei Li

Final-year Ph.D. candidate, University of California, Riverside

prof_pic.jpg

Winston Chung Hall 459

Riverside, US 92507

pli081@ucr.edu, pli2@caltech.edu

I am Pengfei Li, a final-year CS Ph.D. candidate in University of California, Riverside, under the supervision of Prof. Shaolei Ren. Since the summer of 2022, I has been working closely with Adam Wierman at Caltech, focusing on trustworthy learning augmented online optimization. My overarching research goal is to develop trustworthy, equitable and sustainable machine learning systems that enhance the efficiency of real-world systems and address critical societal and environmental challenges.

In the summer 2023, I am fortunate to intern at Nokia Bell Labs mentored by Dr Matthew Andrews, focusing on leveraging diverse IoT sensors to aid autonomous ware-house operations with enhanced dynamic photorealistic digital twins. I obtained a M.S.E degree in Laboratory for Computational Sensing and Robotics (LCSR), Johns Hopkins University, under the supervision of Prof. Alan Yuille and Prof. Gregory Hager. Prior to joining JHU, I graduated from Zhejiang University with honors, majoring in Electrical Engineering. I was also a member of Advanced Class of Engineering Education (ACEE) in Chu Kochen Honor College (CKC).

news

Sep 25, 2024 One paper gets accepted by SIGMSTRICS 2025 🥳🥳🥳 This paper studies decentralized online convex optimization in a networked multi-agent system and proposes a novel learning-augmented online algorithm providing the first contistency-robustness trade-off.
Jun 04, 2024 Two papers accepted by ACM eEnergy 2024, the paper A dataset for research on water sustainability was awarded as Best Notes Paper Award (1 out of 40 submissions).
Nov 28, 2023 Our preprint about LLM water consumption has been covered by Nature Briefing.

selected publications

  1. SIGMETRICS
    EC-L2O.png
    Expert-Calibrated Learning for Online Optimization with Switching Costs
    Pengfei Li*Jianyi Yang*, and Shaolei Ren
    Proceedings of the ACM on Measurement and Analysis of Computing Systems, 2022
  2. CACM
    drought_us.png
    Making AI Less “Thirsty”: Uncovering and Addressing the Secret Water Footprint of AI Models
    Pengfei LiJianyi Yang, Mohammad A. Islam, and 1 more author
    arXiv 2304.03271, 2023
  3. ICML
    LOMAR.jpeg
    Learning for edge-weighted online bipartite matching with robustness guarantees
    Pengfei LiJianyi Yang, and Shaolei Ren
    In Proceedings of the 40th International Conference on Machine Learning, 2023
  4. NeurIPS
    RCL_figure.png
    Robust learning for smoothed online convex optimization with feedback delay
    Pengfei LiJianyi YangAdam Wierman, and 1 more author
    In Proceedings of the 37th International Conference on Neural Information Processing Systems, 2023