Salvato in:
Dettagli Bibliografici
Autori principali: Bolatov, Arman, Horváth, Samuel, Takáč, Martin, Gorbunov, Eduard
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2603.12512
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917337824755712
author Bolatov, Arman
Horváth, Samuel
Takáč, Martin
Gorbunov, Eduard
author_facet Bolatov, Arman
Horváth, Samuel
Takáč, Martin
Gorbunov, Eduard
contents We consider distributed optimization under Byzantine attacks in the presence of $(L_0,L_1)$-smoothness, a generalization of standard $L$-smoothness that captures functions with state-dependent gradient Lipschitz constants. We propose Byz-NSGDM, a normalized stochastic gradient descent method with momentum that achieves robustness against Byzantine workers while maintaining convergence guarantees. Our algorithm combines momentum normalization with Byzantine-robust aggregation enhanced by Nearest Neighbor Mixing (NNM) to handle both the challenges posed by $(L_0,L_1)$-smoothness and Byzantine adversaries. We prove that Byz-NSGDM achieves a convergence rate of $O(K^{-1/4})$ up to a Byzantine bias floor proportional to the robustness coefficient and gradient heterogeneity. Experimental validation on heterogeneous MNIST classification, synthetic $(L_0,L_1)$-smooth optimization, and character-level language modeling with a small GPT model demonstrates the effectiveness of our approach against various Byzantine attack strategies. An ablation study further shows that Byz-NSGDM is robust across a wide range of momentum and learning rate choices.
format Preprint
id arxiv_https___arxiv_org_abs_2603_12512
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Byzantine-Robust Optimization under $(L_0, L_1)$-Smoothness
Bolatov, Arman
Horváth, Samuel
Takáč, Martin
Gorbunov, Eduard
Machine Learning
We consider distributed optimization under Byzantine attacks in the presence of $(L_0,L_1)$-smoothness, a generalization of standard $L$-smoothness that captures functions with state-dependent gradient Lipschitz constants. We propose Byz-NSGDM, a normalized stochastic gradient descent method with momentum that achieves robustness against Byzantine workers while maintaining convergence guarantees. Our algorithm combines momentum normalization with Byzantine-robust aggregation enhanced by Nearest Neighbor Mixing (NNM) to handle both the challenges posed by $(L_0,L_1)$-smoothness and Byzantine adversaries. We prove that Byz-NSGDM achieves a convergence rate of $O(K^{-1/4})$ up to a Byzantine bias floor proportional to the robustness coefficient and gradient heterogeneity. Experimental validation on heterogeneous MNIST classification, synthetic $(L_0,L_1)$-smooth optimization, and character-level language modeling with a small GPT model demonstrates the effectiveness of our approach against various Byzantine attack strategies. An ablation study further shows that Byz-NSGDM is robust across a wide range of momentum and learning rate choices.
title Byzantine-Robust Optimization under $(L_0, L_1)$-Smoothness
topic Machine Learning
url https://arxiv.org/abs/2603.12512