Results

eNauka >  Results >  Large Deviation Upper Bounds and Improved Mse Rates of Nonlinear Sgd: Heavy-Tailed Noise and Power of Symmetry
Title: Large Deviation Upper Bounds and Improved Mse Rates of Nonlinear Sgd: Heavy-Tailed Noise and Power of Symmetry
Authors: Armacki, Aleksandar; Yu, Shuhua; Bajović, Dragana  ; Jakovetić, Dušan; Kar, Soummya
Issue Date: 2026
Publication: SIAM JOURNAL ON OPTIMIZATION
ISSN: 1052-6234 SIAM Journal on Optimization / Society for Industrial and Applied Mathematics Search Idenfier
Publisher: Society for Industrial and Applied Mathematics
Type: Article
Collation: vol. 36 br. 1 str. 32-59
DOI: 10.1137/24M1704154
WoS-ID: 001696217200002
Scopus-ID: 2-s2.0-105030885836
URI: https://enauka.gov.rs/handle/123456789/1032440
URL: https://epubs.siam.org/doi/10.1137/24M1704154
Project: National Science Foundation [ECCS 2330196]
Ministry of Science, Technological Development, and Innovation [451-03-65/2024-03/200156]
Faculty of Technical Sciences, University of Novi Sad [01-3394/1]
Ministry of Science, Technological Development, and Innovation of the Republic of Serbia [451-03-137/2025-03/200125, 451-03-136/2025-03/200125]
Science Fund of Republic of Serbia, project "LASCADO" [7359]
Provincial Secretariat for Higher Education and Scientific Research [142-451-2593/2021-01/2]
Metadata source: (Preuzeto iz Nasi u WoS)
M-category: 
21aM21a

Altmetric
Dimensions
Unpaywall

Items in eNauka are protected by copyright, with all rights reserved, unless otherwise indicated.