Yuezhu Xu

Physics and Astronomy · Purdue University West Lafayette

Established · publishing since 1990Rising activity

Model Reduction and Neural Networks Neural Networks and Applications Generative Adversarial Networks and Image Synthesis High-Velocity Impact and Material Behavior Adversarial Robustness in Machine Learning

Publications

Citations

Est. group size

—

Recurring co-author estimate

Active years

Publishing since 1990

Research summary

AI-generated

Yuezhu Xu works on the mathematical analysis and verification of neural networks, focusing on properties like Lipschitz constants (a measure of how sensitive a network's output is to changes in input) and dissipativity (a stability property borrowed from control theory). This research aims to make neural networks more predictable and safe to use, particularly in settings like automated control systems where guarantees about behavior matter. The work sits at the intersection of machine learning, control theory, and formal verification.

Neural network verification and robustnessLipschitz constant estimationLearning-based control systemsStability and dissipativity of neural dynamical systemsSafe control via reachability analysis

Publication activity began in 2023 and has grown steadily since, rising from 2 papers per year to 4 in 2025, indicating an active and increasing output over the last few years.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026

Publication cadence

Publications per year over the last 10 years — averaging 2.0/year recently

Recent publications

Demystifying Lipschitz verification: positive matrices, negative results
arXiv (Cornell University) · 2026
Demystifying Lipschitz verification: positive matrices, negative results
arXiv (Cornell University) · 2026
ECLipsE-Gen-Local: Efficient Compositional Local Lipschitz Estimates for Deep Neural Networks
arXiv (Cornell University) · 2025
Learning Neural Network Safe Tracking Controllers from Backward Reachable Sets
arXiv (Cornell University) · 2025
ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks
2024
ECLipsE: Efficient Compositional Lipschitz Constant Estimation for Deep Neural Networks
arXiv (Cornell University) · 2024
Learning Dissipative Neural Dynamical Systems
IEEE Control Systems Letters · 2023
Learning Dissipative Neural Dynamical Systems
arXiv (Cornell University) · 2023

Publishes in

arXiv (Cornell University)×7
IEEE Control Systems Letters×1

Similar researchers

By research-topic overlap

Debdipta Goswami
Physics and Astronomy · The Ohio State University
Xihaier Luo
Physics and Astronomy · The Ohio State University
Naxian Ni
Physics and Astronomy · Purdue University West Lafayette
Xiao Wang
Physics and Astronomy · Purdue University West Lafayette
Min Liu
Physics and Astronomy · Purdue University West Lafayette

This profile was generated automatically from public scholarly data (OpenAlex). Group size and activity levels are estimates derived from co-authorship patterns.

Last updated Jul 20, 2026.

Claim or correct this profile