Publications

* denotes equal contribution.

Conference Papers

  • Scaling Laws for Precision in High-Dimensional Linear Regression

    Dechen Zhang, Xuan Tang, Yingyu Liang, Difan Zou

    ICML · 2026

    OpenReview arXiv

  • The Implicit Bias of Steepest Descent with Mini-batch Stochastic Gradient

    Jichu Li, Xuan Tang, Difan Zou

    ICML · 2026

    OpenReview arXiv

  • On the Convergence of Low-Precision LoRA Training

    Dechen Zhang, Xuan Tang, Difan Zou

    ICML HiLD Workshop · 2026

    OpenReview

  • A Convergence Analysis of Adaptive Optimizers under Floating-point Quantization

    Xuan Tang*, Jichu Li*, Difan Zou

    ICLR · 2026

    OpenReview arXiv

  • Understanding the Generalization of Stochastic Gradient Adam in Learning Neural Networks

    Xuan Tang, Han Zhang, Yuan Cao, Difan Zou

    NeurIPS · 2025

    OpenReview arXiv

Preprints

  • VALG: An Agentic System for ML Theory Research

    Dechen Zhang, Xuan Tang, Xinxiang Yin, Xingwu Chen, Jian Qian, Difan Zou

    arXiv preprint · 2026

    arXiv Code