publications

publications by categories in reversed chronological order

2026

  1. One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining
    Philip Zmushko, Egor Petrov, Nikita Abdullaev, and 2 more authors
    In International Conference on Machine Learning (ICML). Equal contribution: P. Zmushko, E. Petrov , 2026
  2. Sign-SGD is the Golden Gate between Multi-Node and Single-Node Learning: Significant Boost via Parameter-Free Optimization
    Daniil Medyakov, Sergey Stanko, Gleb Molodtsov, and 4 more authors
    In International Conference on Learning Representations (ICLR), 2026

2025

  1. Leveraging Coordinate Momentum in SignSGD and Muon: Memory-Optimized Zero-Order LLM Fine-Tuning
    Egor Petrov, Grigoriy Evseev, Aleksey Antonov, and 4 more authors
    In ICML Workshop on Tiny Titans: The next wave of On-Device Learning for Foundation Models, 2025
  2. Closing the Curvature Gap: Full Transformer Hessians and Their Implications for Scaling Laws
    Egor Petrov, Nikita Kiselev, Vladislav Meshkov, and 1 more author
    . Under review at NeurIPS 2026 , 2025
  3. UAI
    When Extragradient Meets PAGE: Bridging Two Giants to Boost Variational Inequalities
    Gleb Molodtsov, Valery Parfenov, Egor Petrov, and 3 more authors
    In The 41st Conference on Uncertainty in Artificial Intelligence, 2025
  4. Sampling of Semi-Orthogonal Matrices for the Muon Algorithm
    Egor Petrov, Grigoriy Evseev, Aleksey Antonov, and 4 more authors
    In Doklady Mathematics. Presented at AI Journey 2025 , 2025

2024

  1. ICOMP
    Shuffling Heuristic in Variational Inequalities: Establishing New Convergence Guarantees
    Daniil Medyakov, Gleb Molodtsov, Grigoriy Evseev, and 2 more authors
    In International Conference on Optimization and Applications (ICOMP). Extended version submitted to the Journal of Optimization Theory and Applications , 2024
  2. Zero Order Algorithm for Decentralized Optimization Problems
    Andrey Sergeevich Veprikov, Egor Dmitrievich Petrov, GV Evseev, and 1 more author
    In Doklady Mathematics. Presented at AI Journey 2024 , 2024