Hanmin Li

Hanmin Li

Ph.D student

KAUST

Biography

I am a CS Ph.D student at King Abdullah University of Science and Technology (KAUST), advised by Prof. Peter Richtárik. My research primarily focuses on optimization, federated learning and machine learning.

Interests
  • Optimization
  • Federated Learning
  • Machine Learning
Education

  • MEng in Computer Science, 2022

    King Abdullah University of Science and Technology

  • BEng in Computer Science and Technology, 2021

    University of Science and Technology of China

Recent Publications

Quickly discover relevant content by filtering publications.
Hanmin Li, Peter Richtárik (2024). On the Convergence of FedProx with Extrapolation and Inexact Prox.

PDF Cite

Hanmin Li, Kirill Acharya, Peter Richtárik (2024). The Power of Extrapolation in Federated Learning.

PDF Cite

Hanmin Li, Avetik Karagulyan, Peter Richtárik (2023). Variance Reduced Distributed Non-Convex Optimization Using Matrix Stepsizes.

PDF Cite

Hanmin Li, Avetik Karagulyan, Peter Richtárik (2023). Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization. ICLR 2024.

PDF Cite

Haoyang Li, Hanmin Li, Juexiao Zhou, Xin Gao (2022). SD2: spatially resolved transcriptomics deconvolution through integration of dropout and spatial information. Bioinformatics.

PDF Cite

Recent & Upcoming Talks

Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization.
This paper introduces a new method for minimizing matrix-smooth non-convex objectives through the use of novel Compressed Gradient …
Jun 28, 2024 8:00 AM Lund
Det-CGD :Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization.
This paper introduces a new method for minimizing matrix-smooth non-convex objectives through the use of novel Compressed Gradient …
May 7, 2024 8:00 AM Vienna

Contact