Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed
Savelii Chezhegov, Yaroslav Klyukin, Andrei Semenov, A. Beznosikov, A. Gasnikov +3 more
2/14/2026
No confident code match yet
We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.
No code implementations found yet.
Know of an implementation? Let us know in the comments below!
@article{chezhegov2026clipping,
title = {Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed},
author = {Savelii Chezhegov and Yaroslav Klyukin and Andrei Semenov and A. Beznosikov and A. Gasnikov and Samuel Horváth and Martin Takác and Eduard Gorbunov},
year = {2026},
url = {https://api.semanticscholar.org/CorpusID:e2706d76ce217380afb4c7e07a61ef2e006fc6f0},
journal = {ICML 2025 2025}
}