Fangzhao Zhang


I am a PhD student in the Department of Electrical Engineering at Stanford University, advised by Stephen Boyd and Mert Pilanci. Prior to joining Stanford, I obtained my bachelor’s degree from the University of British Columbia, majoring in combined honors computer science and math. My research interest lies broadly in convex optimization and deep learning.

I'm open and happy to chat about research ideas :)

  /     /  

Home

Research

  • Solving Large Multicommodity Network Flow Problems on GPUs
    Fangzhao Zhang, Stephen Boyd
    Preprint 2025
    [pdf][code][arXiv]

  • Newton Meets Marchenko-Pastur: Massively Parallel Second-Order Optimization with Hessian Sketching and Debiasing
    Elad Romanov, Fangzhao Zhang, Mert Pilanci
    International Conference on Learning Representations (ICLR) 2025
    [pdf][arXiv]

  • Spectral Adapter: Fine-Tuning in Spectral Space
    Fangzhao Zhang, Mert Pilanci
    Conference on Neural Information Processing System (NeurIPS) 2024
    [pdf] [code][arXiv]

  • Riemannian Preconditioned LoRA for Fine-Tuning Foundation Models
    Fangzhao Zhang, Mert Pilanci
    International Conference on Machine Learning (ICML) 2024
    [pdf] [code][arXiv]

  • Optimal Shrinkage for Distributed Second-Order Optimization
    Fangzhao Zhang, Mert Pilanci
    International Conference on Machine Learning (ICML) 2023
    [pdf][arXiv]

  • Implementation of an Oracle-Structured Bundle Method for Distributed Optimization
    Tetiana Parshakova, Fangzhao Zhang, Stephen Boyd
    Optimization and Engineering 2023
    [pdf] [code] [arXiv]
(* indicates equal contribution)

Teaching

Head TA:   EE364A/CME364A (2024-2025 Winter, Stanford)

Honors

Stanford Graduate Fellowship    Stanford 2021

Governor General's Academic Medal (media cover)   UBC 2021