Resume
Academic Achievements
- - Publications:
- * Towards User-level Private Reinforcement Learning with Human Feedback. COLM 2025.
- * TTVD: Towards a Geometric Framework for Test-Time Adaptation Based on Voronoi Diagram. ICLR 2025.
- * Nearly Optimal Differentially Private ReLU Regression. UAI 2025.
- * Understanding Private Learning From Feature Perspective. ICLR 2025 Workshop.
- * Improved Rates of Differentially Private Nonconvex-Strongly-Concave Minimax Optimization. AAAI 2025.
- * Revisiting Differentially Private ReLU Regression. NeurIPS 2024.
- * Unifying Domain Gap in Federated Learning: a Geometric Approach. Neurocomputing 2024 (Impact Factor: 5.5).
- * Wavelet-Based CNN for Predicting PAP Adherence Using Overnight Polysomnography Recordings: A Pilot Study. EMBC 2021.
- * Benchmarking Various Radiomic Toolkit Features While Applying the Image Biomarker Standardization Initiative toward Clinical Translation of Radiomic Analysis. Journal of Digital Imaging 2021 (Impact Factor: 4.4).
- - Awards:
- * MS Honors Fellow, Ming Hsieh Department of Electrical and Computer Engineering, USC 2021
- * ECE Outstanding Academic Achievement Award, Ming Hsieh Department of Electrical and Computer Engineering, USC 2021
Research Experience
- - Machine Learning Research Intern, CodaMetrix Inc, Boston MA, 06/2025 - 08/2025
Education
- - PhD: Computer Science, University at Buffalo, the State University of New York, Advisor: Prof. Jinhui Xu
- - M.S.: Electrical Engineering, University of Southern California, Advisor: Prof. Keith Jenkins
- - B.Eng.: Guangdong University of Technology, China
Background
- - Research Interest: Large Language Models, Trustworthy Machine Learning (Generalization, Privacy), Online/Continuous Learning, Post-training (Adaptation)
- - Professional Field: Computer Science
- - Brief Introduction: Mingxi Lei is a PhD student in the Department of Computer Science and Engineering at the University at Buffalo, supervised by Prof. Jinhui Xu.
Miscellany
- - Teaching Experience:
- * CSE 676 Deep Learning, Spring 2023
- * CSE 574 Intro to Machine Learning, Fall 2022
- * CSE 250 Data Structure, Spring 2022
- * CSE 4/528 Intro to Digital Image Processing, Fall 2021
- * CSCI 467 Intro to Machine Learning (Course Producer), USC, Spring 2021
- - Professional Services:
- * Journal Reviews: IEEE Journal of Biomedical and Health Informatics (JBHI), BMC Medical Imaging
- * Conference Reviews: NeurIPS, ICLR, SoCG, AAAI