About me

Hi, I am a Ph.D student in System Engineering at Boston University, supervised by Prof. Francesco Orabona. I am a member of OPTIMAL Lab.

My research interests lie in theoretical machine learning and stochastic optimization. I currently work on understanding and designing optimization methods in machine learning, specifically, stochastic gradient descent and its variants, and adaptive gradient descent methods.

I received my Bachelor degree in Math and Applied Math from University of Science and Technology of China.


Publications and Preprints

  • A High Probability Analysis of Adaptive SGD with Momentum.
    Xiaoyu Li, Francesco Orabona. ICML Workshop on Beyond First Order Methods in ML Systems, 2020. Paper Video

  • Exponential Step Sizes for Non-Convex SGD.
    Xiaoyu Li, Zhenxun Zhuang, Francesco Orabona. arXiv preprints Feb. 2020. Paper Code

  • On the Convergence of Stochastic Gradient Descent with Adaptive Stepsizes.
    Xiaoyu Li, Francesco Orabona. In International Conference on Artificial Intelligence and Statistics (AISTATS), 2019. Paper



Research Intern @ Nokia Bell Labs, Murray Hill, NJ.
Host: Carl Nuzman June - Aug. 2019

Academic Service

Reviewer of NeurIPS2019 \& 2020; AISTATS2020, ICML2020