Liang Zhang

About

I am a third-year Ph.D. student in computer science at the Max Planck ETH Center for Learning Systems, jointly advised by Niao He from ETH Zurich and Michael Muehlebach from the Max Planck Institute for Intelligent Systems. I also closely collaborate with Sewoong Oh from University of Washington and Kiran Koshy Thekumparampil from Amazon.

My research focus lies in the intersection between optimization and machine learning. I have a keen interest in developing efficient optimization algorithms for trustworthy machine learning.

Prior to this, I received my master's degree in computer science from ETH Zurich in 2021 and bachelor's degree in physics from Peking University in 2019.

Publications

Preprint

• A Hessian-Aware Stochastic Differential Equation for Modelling SGD.
  Xiang Li, Zebang Shen, Liang Zhang, Niao He.
  Working Paper [arXiv] [HiLD@ICML'24]

Journal Article

• Primal Methods for Variational Inequality Problems with Functional Constraints.
  Liang Zhang, Niao He, Michael Muehlebach.
  Math. Program., 2025 [Springer] [arXiv]

Conference Paper

• On the Crucial Role of Initialization for Matrix Factorization.
  Bingcong Li, Liang Zhang, Aryan Mokhtari, Niao He.
  ICLR, 2025 [OpenReview] [arXiv] [OPT-ML@NeurIPS'24] [CPAL'25]
• Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems.
  Bingcong Li, Liang Zhang, Niao He.
  NeurIPS, 2024 [NeurIPS] [OpenReview] [arXiv] [TF2M@ICML'24]
• DPZero: Private Fine-Tuning of Language Models without Backpropagation.
  Liang Zhang, Bingcong Li, Kiran Koshy Thekumparampil, Sewoong Oh, Niao He.
  ICML, 2024 [ICML] [OpenReview] [arXiv] [GitHub] [Video] [FL-FM@NeurIPS'23] [FORC'24] [TPDP'24]
• Generalization Bounds of Nonconvex-(Strongly)-Concave Stochastic Minimax Optimization.
  Siqi Zhang*, Yifan Hu*, Liang Zhang, Niao He.
  AISTATS, 2024 [AISTATS] [arXiv] [OPT-ML@NeurIPS'22]
• Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization.
  Liang Zhang*, Junchi Yang*, Amin Karbasi, Niao He.
  NeurIPS, 2023 (Spotlight) [NeurIPS] [OpenReview] [arXiv]
• Bring Your Own Algorithm for Optimal Differentially Private Stochastic Minimax Optimization.
  Liang Zhang, Kiran Koshy Thekumparampil, Sewoong Oh, Niao He.
  NeurIPS, 2022 [NeurIPS] [OpenReview] [arXiv]

Thesis

• Variance Reduction for Non-Convex Stochastic Optimization: General Analysis and New Applications.
  Master Thesis [ETH]. Supervised by Yifan Hu and Niao He.

Presentations

• Conference on Parsimony and Learning (CPAL) 2025, Stanford. Poster presentation on LoRA initialization (NoRA).
• Theory and Practice of Differential Privacy (TPDP) 2024, Boston. Poster presentation on DPZero.
• SIAM Conference on Optimization (OP23), Seattle. Talk on differentially private stochastic minimax optimization.

Teaching Assistant

• Optimization for Data Science (Spring 2024), ETH Zurich.
• Foundations of Reinforcement Learning (Autumn 2021, Spring 2023), ETH Zurich.
• Large-Scale Convex Optimization (Spring 2025), ETH Zurich.
• Big Data (Autumn 2024), ETH Zurich.

Project Supervision

• Lejs Behric, bachelor thesis at ETH Zurich, 2024 (co-supervised with Bingcong Li and Kiran Koshy Thekumparampil).
  Topic: Fine-tuning LLMs with Efficient Zeroth-Order Optimization.
• Nikolija Bojkovic, Student Summer Research Fellowship at ETH Zurich, 2024 (co-supervised with Bingcong Li).
  Topic: Differentially Private Stochastic Zeroth-Order Optimization.
• Lukas Altun, bachelor thesis at ETH Zurich, 2024 (co-supervised with Bingcong Li).
  Topic: Computationally Efficient Sharpness-Aware Minimization.
• Martin Mason, bachelor thesis at ETH Zurich, 2023.
  Topic: Exploring Gradient Clipping in Private Machine Learning.

Service

• Reviewers for JMLR, NeurIPS (2023, 2024, 2025), ICLR (2023, 2024, 2025), ICML (2024, 2025), and AISTATS (2025).
• Top reviewers for NeurIPS (2024).