Scholar
Peizhong Ju
Google Scholar ID: VDzpfOYAAAAJ
Assistant Professor of Computer Science, University of Kentucky
Citations & Impact
Citations
270
H-index
10
i10-index
10
Publications
20
Co-authors
8
list available
Publications
Resume (English only)
Academic Achievements
- On July 25, 2025, one paper on classification on edge devices was accepted by ACM MobiHoc'25; On May 1, 2025, two papers were accepted by ICML'25: one on federated split learning and another on continual learning; On February 28, 2025, presented PSMGD work and chaired an oral session at AAAI'25; On February 11, 2025, the paper 'How to Find the Exact Pareto Front for Multi-Objective MDPs?' was selected as a Spotlight (5.1% of the submitted papers) by ICLR'25; On January 22, 2025, three papers were accepted by ICLR'25: two focused on diffusion models and one exploring multi-objective MDPs; On January 15-16, 2025, attended the NeTS Early Career Workshop 2025 at NSF in Alexandria, VA; On December 9, 2024, a research paper on Fast Multi-Objective Optimization was accepted to AAAI'25; On July 28, 2024, two papers were accepted by MobiHoc'24: one on Federated Learning and another on network-edge classification; On January 16, 2024, two papers on Reinforcement Learning were accepted by ICLR'24; On July 27, 2023, presented continual learning work with Sen Lin at ICML'23; On July 20, 2023, The Ohio State University News reported their continual learning research in a press release: 'Future AI algorithms have potential to learn like humans, say researchers.'
Research Experience
- Assistant Professor at the Department of Computer Science, University of Kentucky, 2024 - Present; Postdoctoral Scholar at the ECE department, The Ohio State University, 2021 - 2024; Involved in NSF AI Institute on Future Edge Networks and Distributed Intelligence (AI-EDGE).
Education
- B.Sc. in Electrical Engineering from Peking University in 2016; Ph.D. in Electrical and Computer Engineering from Purdue University in 2021.
Background
- Research interests include machine learning, smart grid, optimization, and wireless communication. Recent research focuses on theories for explaining the performance of machine learning models. Previously worked on power systems and wireless communication. The goal of his research is to use rigorous mathematical analysis (including probability theory, optimization, game theory, and random matrix theory) to understand the fundamental limits of a complex system under uncertainty and/or disturbance.
Miscellany
- Contact information: peizhong.ju@uky.edu; Office location and phone number are available on the faculty webpage at the University of Kentucky; CV (as a pdf file) is here (Last updated: Sep 1, 2025); Check out Google Scholar profile for a list of publications.
