Chang He (何畅)

I am a Ph.D. student in the Department of Industrial and Systems Engineering at the University of Minnesota Twin Cities, advised by Prof. Shuzhong Zhang. I also work closely with Prof. Mingyi Hong and Prof. Shancong Mou. My research interests lie in continuous optimization, with applications in machine learning and operations research. In particular, I work on the following topics: Efficient Optimization Algorithm Design Worst-Case Complexity Analysis E-mail: hec [at] umn [dot] edu / ischanghe [at] gmail [dot] com Google Scholar

Selected Works

• New Results on the Polyak Stepsize: Tight Convergence Analysis and Universal Function Classes
  Chang He∗, Wenzhi Gao∗, Bo Jiang, Madeleine Udell, and Shuzhong Zhang
  SIAM Journal on Optimization, accepted, 2026

• History-Aware Adaptive High-Order Tensor Regularization
  Chang He, Bo Jiang, Yuntian Jiang, Chuwen Zhang, and Shuzhong Zhang (α–β)
  Preprint, 2025

• Non-Stationary Bandit Convex Optimization: An Optimal Algorithm with Two-Point Feedback
  Chang He, Bo Jiang, and Shuzhong Zhang
  Preprint, 2025

• Homogeneous Second-Order Descent Framework: A Fast Alternative to Newton-Type Methods
  Chang He∗, Yuntian Jiang∗, Chuwen Zhang∗, Dongdong Ge, Bo Jiang, and Yinyu Ye
  Mathematical Programming, 2025. Slides
  2025 iSoGO Student Paper Award.

• Riemannian Accelerated Zeroth-Order Algorithm: Improved Robustness and Lower Query Complexity
  Chang He, Zhaoye Pan, Xiao Wang, and Bo Jiang
  International Conference on Machine Learning, 2024

∗ Equal contribution.

View all publications

Service

• Referee for Journal of Global Optimization

• Referee for Linear Algebra and its Applications

• Referee for Mathematics of Operations Research

• Referee for IEEE Transactions on Automatic Control

• Referee for SIAM Journal on Optimization

• Referee for Communications on Applied Mathematics and Computation

• Referee for AISTATS 2026 and NeurIPS 2026