Skip to content
View modernTalker's full-sized avatar
0 followers · 1 following

Block or report modernTalker

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
modernTalker/README.md

Email Google Scholar

Research Interests

  • Loss Landscape: Empirical & theoretical analysis in pipeline and distributed settings; connections to loss landscape geometry (e.g., Hessian spectrum of Transformers)
  • One-Step delayed Optimization: Scheduling, memory optimization, and convergence guarantees under asynchrony
  • Zeroth- and First-Order Methods: Advancing zeroth-order (ZO) and first-order algorithms for smooth, non-convex problems

🎓 B.S. in Applied Mathematics & Informatics @ MIPT (2022–2026)

🚀 Yandex Research Residency @ YR (2025-2026)

🎯 Data Science Track (MIPT & Yandex SDA, 2024–2026) @ DS (2023-2026)

🌊 BRAIn Lab @ MIRIAI (2024 - 2026)

🧑‍🏫 Teaching Assistant: Algorithms, Data Structures, Scientific Studio

Pinned Loading

  1. zero-order-optimization zero-order-optimization Public

    Library with various Zero-Order Optimization methods implemented in torch-like format

    Python 3 2

  2. Closing-the-Curvature-Gap Closing-the-Curvature-Gap Public

    Official paper "Closing the Curvature Gap: Full Transformer Hessians and Their Implications for Scaling Laws" github

    TeX