Publications

* denotes equal contributions.

Conference Publications

• Adagrad Under Anisotropic Smoothness.
  Yuxing Liu*, Rui Pan*, and Tong Zhang. [ICLR 2025]
• Decentralized Convex Finite-Sum Optimization with Better Dependence on Condition Numbers.
  Yuxing Liu, Lesi Chen, and Luo Luo. [ICML 2024]
• On the Complexity of Finite-Sum Smooth Optimization under the Polyak-Lojasiewicz Condition.
  Yunyan Bai, Yuxing Liu, and Luo Luo. [ICML 2024]
• Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise.
  Rui Pan*, Yuxing Liu*, Xiaoyu Wang, and Tong Zhang. [ICLR 2024]

Preprints

• Theoretical Analysis on how Learning Rate Warmup Accelerates Convergence.
  Yuxing Liu*, Yuze Ge, Rui Pan, Kang An, and Tong Zhang. [arXiv]
• Asgo: Adaptive structured gradient optimization.
  Kang An*, Yuxing Liu*, Rui Pan, Yi Ren, Shiqian Ma, Donald Goldfarb, and Tong Zhang. [arXiv]
• On the Complexity of Decentralized Smooth Nonconvex Finite-Sum Optimization.
  Luo Luo, Yunyan Bai, Lesi Chen, Yuxing Liu, and Haishan Ye. [arXiv]