Pengfei Li

I am Pengfei Li, a fourth-year CS Ph.D. student in University of California, Riverside, under the supervision of Prof. Shaolei Ren. Recently, we also work closely with Adam Wierman on online optimization problems. 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). In summer 2017, I took part in the International Summer Research Program in UCSD under the supervision of Prof. Atanasov as a research intern.

Email / Twitter / Github / CV / Google Scholar/ LinkedIn

profile photo

News

Publications (* denotes equal contribution)
Building Socially-Equitable Public Models [arxiv ][code]
Yejia Liu, Jianyi Yang, Pengfei Li, Tongxin Li, Shaolei Ren
ICML, 2024
A dataset for research on water sustainability [arxiv] [data]
Pranjol Sen Gupta, Md Rajib Hossen, Pengfei Li, Shaolei Ren, Mohammad A. Islam
ACM eEnergy, 2024 (Best Notes Paper Award)
Towards Environmentally Equitable AI via Geographical Load Balancing [arxiv ][code]
Pengfei Li, Jianyi Yang, Adam Wierman, Shaolei Ren
eEnergy-2024
Online Allocation with Replenishable Budgets: Worst Case and Beyond [paper]
Jianyi Yang, Pengfei Li, Mohammad J. Islam, Shaolei Ren
SIGMETRICS, 2024
Robust Learning for Smoothed Online Convex Optimization with Feedback Delay [paper ][video ]
Pengfei Li, Jianyi Yang, Adam Wierman, Shaolei Ren
NuerIPS, 2023
Anytime-Constrained Reinforcement Learning with Policy Prior [paper][video]
Jianyi Yang, Pengfei Li, Tongxin Li, Adam Wierman, Shaolei Ren
NuerIPS, 2023
Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees [arxiv][code][video]
Pengfei Li, Jianyi Yang, Shaolei Ren
ICML, 2023
Making AI Less "Thirsty": Uncovering and Addressing the Secret Water Footprint of AI Models [ arxiv][code]
Pengfei Li, Jianyi Yang, Mohammad A. Islam, Shaolei Ren
Communications of the ACM (to be appeared)
The Guardian / CBC News / Associate Press
Expert-Calibrated Learning for Online Optimization with Switching Costs[paper][abstract][arxiv][video][code ]
Pengfei Li*, Jianyi Yang*, Shaolei Ren
SIGMETRICS, 2022
Expert-Robustified Learning for Online Optimization with Memory Cost.[paper][arxiv]
Pengfei Li, Jianyi Yang, Shaolei Ren
INFOCOM, 2023
Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry [paper][video][code]
He Chen*, Pengfei Guo*, Pengfei Li, Gim Hee Lee, Gregory Chirikjian
ECCV, 2020 (Spotlight)


Highlighted Research

My research interests mainly focus on Nonlinear Optimization, Machine Learning and Graph Theory. Representative papers are highlighted, * indicates equal contributions.

Towards Environmentally Equitable AI via Geographical Load Balancing
Pengfei Li, Jianyi Yang, Adam Wierman, Shaolei Ren
ACM eEnergy, 2024
arxiv /code

While many approaches have been proposed to make AI more energy-efficient and environmentally friendly, environmental inequity -- the fact that AI's environmental footprint can be disproportionately higher in certain regions than in others. This paper takes a first step toward addressing AI's environmental inequity by balancing its regional negative environmental impact.

Robust Learning for Smoothed Online Convex Optimization with Feedback Delay
Pengfei Li, Jianyi Yang, Adam Wierman, Shaolei Ren
NuerIPS, 2023
paper / video

We study the most general form of Smoothed Online Convex Optimization, a.k.a. SOCO, including multi-step nonlinear switching costs and feedback delay. We propose a novel machine learning (ML) augmented online algorithm, Robustness-Constrained Learning(RCL). Importantly, RCL is the first ML-augmented algorithm with a provable robustness guarantee in the case of multi-step switching cost and feedback delay.

Making AI Less "Thirsty": Uncovering and Addressing the Secret Water Footprint of AI Models
Pengfei Li, Jianyi Yang, Mohammad A. Islam, Shaolei Ren
arXiv:2304.03271
code / arxiv / The Guardian / CBC News / Associate Press

The growing carbon footprint of large artificial intelligence (AI) models, such as GPT-3, has been undergoing public scrutiny. Unfortunately, however, the equally important and enormous water footprint of AI models has remained under the radar. We highlight the necessity of holistically addressing water footprint along with carbon footprint to enable truly sustainable AI.

Learning for Edge-Weighted Online Bipartite Matching with Robustness Guarantees
Pengfei Li, Jianyi Yang, Shaolei Ren
ICML, 2023
arxiv / code / slides

A novel RL-based approach for edge-weighted online bipartite matching with robustness guarantees, achieving both good average-case performance and strict worst-case guarantee. This framework (LOMAR) supports training the RL policy by explicitly considering the online robustification operation.

Expert-Calibrated Learning for Online Optimization with Switching Costs
Pengfei Li*, Jianyi Yang*, Shaolei Ren
SIGMETRICS, 2022
paper / abstract / arxiv / video / slides / code

EC-L2O is the first to address the "how to learn" challenge for online convex optimization, which requires new algorithm design, closed-form differentiation and theoritical analysis.

Multi-person 3D Pose Estimation in Crowded Scenes Based on Multi-View Geometry
He Chen*, Pengfei Guo*, Pengfei Li, Gim Hee Lee, Gregory Chirikjian
ECCV, spotlight, 2020
paper / video / code

A novel 3D crowd human pose estimation method, which proposed a faster cross-view matching based on graphical model


Misc
Reviewer/PC:
ICDCS 2024
AAAI 2024
IEEE/ACM Transactions on Networking 2024
IEEE Systems Journal 2023
IEEE Transactions on Green Communications and Networking 2023
IEEE Transactions on Mobile Computing 2023
IEEE Transactions on Computational Social Systems 2024
Membership:
IEEE Student Member
IEEE ComSoc Student Member
ACM Student Member
cs188 Graduate Student Instructor
CS010B Fall 2021
CS010B Winter 2021
CS010B Spring 2021

Visitors from the world



┬ęPengfei Li, last updated June 2024.
Template from Jon Barron.