Work

Accelerated Stochastic Method under $(H_0,H_1)$-Smoothness and Heavy-Tailed Noise

Year: 2026

Type: preprint

Abstract: We develop an accelerated stochastic method for convex $(H_0,H_1)$-smooth optimization under heavy-tailed noise. The unbiased oracle has a finite $p$-th noise moment, $1

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2609.33415

Authors: Lobanov, Aleksandr, Dvinskikh, Darina, Gasnikov, Alexander

Institutions: National Research University Higher School of Economics, Innopolis University

Language: English

Topic: Stochastic Gradient Optimization Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7214721777

Cites:

Cited by:

Related to: 10