Wenzhi Gao

Contact

Huang Engineering Center
475 Via Ortega, Stanford, CA 94305
Email: gwz@stanford.edu
Website: https://web.stanford.edu/~gwz/

About

I am a third-year Ph.D. student in the Institute for Computational and Mathematical Engineering (ICME) at Stanford University advised by Professor Madeleine Udell. I also work closely with Professor Yinyu Ye. My research focuses on large-scale numerical optimization, online sequential decision-making, and stochastic first-order methods.

You can find my full list of publications on Google Scholar or here, and download my latest CV (PDF).

Research Interests

• Large-scale numerical optimization
• Online convex optimization and sequential decision-making
• Stochastic and adaptive first-order methods

Selected Publications

1. Gradient Methods with Online Scaling.
   W. Gao, YC. Chu, Y. Ye, M. Udell.
   COLT 2025. Code available at https://github.com/udellgroup/osgm-best-hypergrad.
2. Gradient Methods with Online Scaling. Part I. Theoretical Foundations.
   W. Gao, YC. Chu, Y. Ye, M. Udell.
   Preprint, 2025.
3. Gradient Methods with Online Scaling. Part II. Practical Aspects.
   YC. Chu, W. Gao, Y. Ye, M. Udell.
   Preprint, 2025.
4. Beyond $\mathcal{O}(\sqrt{T})$ Regret: Decoupling Learning and Decision-making in Online Linear Programming.
   W. Gao, D. Ge, C. Sun, C. Xue, Y. Ye.
   Accepted by Operations Research, 2026.

See the papers page for the complete list.

Academic Service

• Reviewer of Journals: Operations Research, TMLR, AJCN
• Reviewer of Conferences: NeurIPS, ICML, ICLR, AISTATS, AAAI, KDD, NLDL
• Session Chair: INFORMS Annual Meeting 2024 (Seattle)

Talks and Presentations

• “When Does Primal/dual IPM Beat Primal-Dual?” INFORMS OPTIMIZATION SOCIETY CONFERENCE 2026（Atlanta)
• “Gradient Methods with Online Scaling,” INFORMS 2025 (Atlanta) & ICCOPT 2025 (Los Angeles)
• “Beyond $\mathcal{O}(\sqrt{T})$ Regret in Online Linear Programming,” INFORMS 2025 (Atlanta)
• “When Does Primal IPM Beat Primal-Dual?” INFORMS 2024 (Seattle) & MOPTA 2024 (Lehigh)

Skills

Python, Matlab, C; Optimization tools: Gurobi, COPT, CPLEX, MOSEK, SCIP