Rustem Islamov

According to our database, Rustem Islamov authored at least 24 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

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

Rustem Islamov, Grigory Malinovsky, Alexander Gaponov, Aurélien Lucchi, Peter Richtárik, Eduard Gorbunov

CoRR, March, 2026

On the Role of Batch Size in Stochastic Conditional Gradient Methods.

Rustem Islamov, Roman Machacek, Aurélien Lucchi, Antonio Silveti-Falls, Eduard Gorbunov, Volkan Cevher

CoRR, March, 2026

Non-Euclidean Gradient Descent Operates at the Edge of Stability.

Rustem Islamov, Michael Crawshaw, Jeremy Cohen, Robert M. Gower

CoRR, March, 2026

Adaptive Methods Are Preferable in High Privacy Settings: An SDE Perspective.

Enea Monzio Compagnoni, Alessandro Stanghellini, Rustem Islamov, Aurélien Lucchi, Anastasiia Koloskova

CoRR, March, 2026

2025

Why Do We Need Warm-up? A Theoretical Perspective.

Foivos Alimisis, Rustem Islamov, Aurélien Lucchi

CoRR, October, 2025

Enhancing Optimizer Stability: Momentum Adaptation of The NGN Step-size.

Rustem Islamov, Niccolò Ajroldi, Antonio Orvieto, Aurélien Lucchi

CoRR, August, 2025

On the Interaction of Noise, Compression Role, and Adaptivity under (L₀, L₁)-Smoothness: An SDE-based Approach.

Enea Monzio Compagnoni, Rustem Islamov, Antonio Orvieto, Eduard Gorbunov

CoRR, June, 2025

Safe-EF: Error Feedback for Nonsmooth Constrained Optimization.

Rustem Islamov, Yarden As, Ilyas Fatkhullin

CoRR, May, 2025

Double Momentum and Error Feedback for Clipping with Fast Rates and Differential Privacy.

Rustem Islamov, Samuel Horváth, Aurélien Lucchi, Peter Richtárik, Eduard Gorbunov

CoRR, February, 2025

Partially Personalized Federated Learning: Breaking the Curse of Data Heterogeneity.

Konstantin Mishchenko, Rustem Islamov, Eduard Gorbunov, Samuel Horváth

Trans. Mach. Learn. Res., 2025

Safe-EF: Error Feedback for Non-smooth Constrained Optimization.

Rustem Islamov, Yarden As, Ilyas Fatkhullin

Proceedings of the Forty-second International Conference on Machine Learning, 2025

Towards Faster Decentralized Stochastic Optimization with Communication Compression.

Rustem Islamov, Yuan Gao, Sebastian U. Stich

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise.

Enea Monzio Compagnoni, Tianlin Liu, Rustem Islamov, Frank Norbert Proske, Antonio Orvieto, Aurélien Lucchi

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Unbiased and Sign Compression in Distributed Learning: Comparing Noise Resilience via SDEs.

Enea Monzio Compagnoni, Rustem Islamov, Frank Norbert Proske, Aurélien Lucchi

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2025

2024

Near Optimal Decentralized Optimization with Compression and Momentum Tracking.

Rustem Islamov, Yuan Gao, Sebastian U. Stich

CoRR, 2024

Loss Landscape Characterization of Neural Networks without Over-Parametrization.

Rustem Islamov, Niccolò Ajroldi, Antonio Orvieto, Aurélien Lucchi

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

EControl: Fast Distributed Optimization with Compression and Error Control.

Yuan Gao, Rustem Islamov, Sebastian U. Stich

Proceedings of the Twelfth International Conference on Learning Representations, 2024

AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms.

Rustem Islamov, Mher Safaryan, Dan Alistarh

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2024

2023

Adaptive Compression for Communication-Efficient Distributed Training.

Maksim Makarenko, Elnur Gasanov, Abdurakhmon Sadiev, Rustem Islamov, Peter Richtárik

Trans. Mach. Learn. Res., 2023

Distributed Newton-Type Methods with Communication Compression and Bernoulli Aggregation.

Rustem Islamov, Xun Qian, Slavomír Hanzely, Mher Safaryan, Peter Richtárik

Trans. Mach. Learn. Res., 2023

Clip21: Error Feedback for Gradient Clipping.

Sarit Khirirat, Eduard Gorbunov, Samuel Horváth, Rustem Islamov, Fakhri Karray, Peter Richtárik

CoRR, 2023

2022

FedNL: Making Newton-Type Methods Applicable to Federated Learning.

Mher Safaryan, Rustem Islamov, Xun Qian, Peter Richtárik

Proceedings of the International Conference on Machine Learning, 2022

Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning.

Xun Qian, Rustem Islamov, Mher Safaryan, Peter Richtárik

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

2021

Distributed Second Order Methods with Fast Rates and Compressed Communication.

Rustem Islamov, Xun Qian, Peter Richtárik

Proceedings of the 38th International Conference on Machine Learning, 2021