Alexey Voronin

alexey-voronin.png

I am a Senior Member of Technical Staff in the Center for Computing Research (CCR) at Sandia National Laboratories. I develop nonlinear and linear solvers and preconditioners for optimal control of Maxwell’s equations. In scientific machine learning, I use classical methods such as spectral analysis and domain decomposition to make neural network training faster, cheaper, and more accurate.

I earned my PhD in Computer Science from the University of Illinois at Urbana-Champaign. Before that, I spent three years as a software engineer at Lawrence Livermore National Laboratory, working on multiphysics simulation codes for GPUs and modern HPC architectures.

The best way to keep up with my work is through Google Scholar and GitHub.

selected publications

  1. ntk.png
    On the convergence behavior of preconditioned gradient descent toward the rich learning regime
    Shuai Jiang , Alexey Voronin, Eric Cyr , and 1 more author
    In International Conference on Learning Representations , 2026
  2. high_order_mg.png
    Monolithic Multigrid Preconditioners for High-Order Discretizations of Stokes Equations
    Alexey Voronin, Graham Harper , Scott MacLachlan , and 2 more authors
    2024
  3. artery.png
    Monolithic Algebraic Multigrid Preconditioners for the Stokes Equations
    Alexey Voronin, Scott MacLachlan , Luke N. Olson , and 1 more author
    Arxiv, 2023