Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Rustem Islamov

Rustem Islamov

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

ML×2Optimization and Control×2Stats ML×1Crypto×1

Frequent co-authors

Aurelien Lucchi2×
Eduard Gorbunov2×
Kumar Kshitij Patel1×
Sebastian U Stich1×
Lingxiao Wang1×
Grigory Malinovsky1×

Research Timeline

2026
Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions

The paper proposes Byz-Clip21-SGD2M, a novel algorithm that achieves high-probability convergence guarantees for Federated Learning by integrating robust aggregation, double momentum, and clipping, relaxing restrictive assumptions found in prior work.

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity

This paper proves the conjecture that Local SGD outperforms Mini-batch SGD under bounded second-order heterogeneity for general convex objectives, improving the convergence guarantee and lower bounds.

Highlighted terms show continued research focus across papers

Papers

cs.LGmath.OCstat.MLTheoreticalRecentJul 16, 2026

What's in a Smoothness Constant? Tighter Rates for Local SGD with Bounded Second-order Heterogeneity

Kumar Kshitij Patel, Rustem Islamov, Sebastian U Stich, Aurelien Lucchi +2 more

This paper proves the conjecture that Local SGD outperforms Mini-batch SGD under bounded second-order heterogeneity for general convex objectives, improving the convergence guarantee and lower bounds.

View →
cs.LGcs.CRmath.OCRecent
Mar 24, 2026

Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions

Rustem Islamov, Grigory Malinovsky, Alexander Gaponov, Aurelien Lucchi +2 more

The paper proposes Byz-Clip21-SGD2M, a novel algorithm that achieves high-probability convergence guarantees for Federated Learning by integrating robust aggregation, double momentum, and clipping, re…

View →