1. The Ball-Proximal (=”Broximal”) Point Method: a New Algorithm, Convergence Theory, and Applications

    Kaja Gruntkowska, Hanmin Li, Aadi Rane, Peter Richtárik, arXiv preprint. · paper · BibTeX

  2. The Power of Extrapolation in Federated Learning

    Hanmin Li, Kirill Acharya, and Peter Richtárik., NeurIPS 2024. · paper · BibTeX

  3. On the Convergence of FedProx with Extrapolation and Inexact Prox

    Hanmin Li, and Peter Richtárik., NeurIPS 2024 OPT-ML Workshop Poster. · paper · BibTeX

  4. Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization

    Hanmin Li, Avetik Karagulyan, Peter Richtárik, ICLR 2024. · paper · BibTeX

  5. Variance reduced distributed non-convex optimization using matrix stepsizes

    Hanmin Li, Avetik Karagulyan, Peter Richtárik, NeurIPS 2023 FL@FM Workshop. · paper · BibTeX

  6. SD2: spatially resolved transcriptomics deconvolution through integration of dropout and spatial information

    Haoyang Li, Hanmin Li, Juexiao Zhou, Xin Gao, Bioinformatics. · paper · BibTeX