Weak-$L^α$ Noise, Strong Guarantees: Gradient Clipping under Affine Heavy Tails
Overview & Synopsis
Gradient clipping is a key tool for obtaining high-probability convergence guarantees for stochastic first-order methods under heavy-tailed noise. Existing analyses typically assume a bounded central moment of order $α\in(1,2]$, which excludes distributions with tails of order $u^{-α}$ at the critical exponent. In this paper, we consider smooth convex optimization under affine heavy-tailed noise, whose scale may grow with the gradient norm. We derive high-probability convergence guarantees for clipped SGD (Clip-SGD) and its accelerated variant Clip-SSTM under a weak-$L^α$ tail condition, which is strictly weaker than the corresponding moment bound. For $1
Indexed from repository: arXiv
(
arxiv.org)
Keyboard Shortcuts:
← / → for pages • + / - for zoom • 0 to fit width
Powered by Mozilla PDF.js v3.11
Document Information
| Document Title | Weak-$L^α$ Noise, Strong Guarantees: Gradient Clipping under Affine Heavy Tails |
|---|---|
| Author / Organization | Alyona Nekrasova, Makar Sidorov, Savelii Chezhegov, Alexander Gasnikov, Margarita Preobrazhenskaia, Igor Preobrazhensky, Eduard Gorbunov |
| Subject & Discipline | math.OC |
| Categories | Science & Mathematics |
| Publication Year | 2026 |
| License / Rights | arXiv Open Access / Creative Commons |
| Resource Verification | Listed PDF (Verification Pending) |
| Original Host Website |
arXiv
(arxiv.org)
|
| File Format | application/pdf (Portable Document Format) |
| Language | EN |
| Catalog ID | DOC-269992 |
| Original Source Link | Visit Source Page on arxiv.org » |