Risultati della ricerca - Islamov, Rustem

Safe-EF: Error Feedback for Nonsmooth Constrained Optimization di Islamov, Rustem, As, Yarden, Fatkhullin, Ilyas

Testo

Why Do We Need Warm-up? A Theoretical Perspective di Alimisis, Foivos, Islamov, Rustem, Lucchi, Aurelien

Testo

Towards Faster Decentralized Stochastic Optimization with Communication Compression di Islamov, Rustem, Gao, Yuan, Stich, Sebastian U.

Testo

Loss Landscape Characterization of Neural Networks without Over-Parametrization di Islamov, Rustem, Ajroldi, Niccolò, Orvieto, Antonio, Lucchi, Aurelien

Testo

Enhancing Optimizer Stability: Momentum Adaptation of The NGN Step-size di Islamov, Rustem, Ajroldi, Niccolo, Orvieto, Antonio, Lucchi, Aurelien

Testo

Non-Euclidean Gradient Descent Operates at the Edge of Stability di Islamov, Rustem, Crawshaw, Michael, Cohen, Jeremy, Gower, Robert

Testo

Double Momentum and Error Feedback for Clipping with Fast Rates and Differential Privacy di Islamov, Rustem, Horvath, Samuel, Lucchi, Aurelien, Richtarik, Peter, Gorbunov, Eduard

Testo

Unbiased and Sign Compression in Distributed Learning: Comparing Noise Resilience via SDEs di Compagnoni, Enea Monzio, Islamov, Rustem, Proske, Frank Norbert, Lucchi, Aurelien

Testo

Adaptive Methods Are Preferable in High Privacy Settings: An SDE Perspective di Compagnoni, Enea Monzio, Stanghellini, Alessandro, Islamov, Rustem, Lucchi, Aurelien, Koloskova, Anastasiia

Testo

Byzantine-Robust and Differentially Private Federated Optimization under Weaker Assumptions di Islamov, Rustem, Malinovsky, Grigory, Gaponov, Alexander, Lucchi, Aurelien, Richtárik, Peter, Gorbunov, Eduard

Testo

On the Role of Batch Size in Stochastic Conditional Gradient Methods di Islamov, Rustem, Machacek, Roman, Lucchi, Aurelien, Silveti-Falls, Antonio, Gorbunov, Eduard, Cevher, Volkan

Testo

Adaptive Methods through the Lens of SDEs: Theoretical Insights on the Role of Noise di Compagnoni, Enea Monzio, Liu, Tianlin, Islamov, Rustem, Proske, Frank Norbert, Orvieto, Antonio, Lucchi, Aurelien

Testo

On the Interaction of Batch Noise, Adaptivity, and Compression, under $(L_0,L_1)$-Smoothness: An SDE Approach di Compagnoni, Enea Monzio, Islamov, Rustem, Proske, Frank Norbert, Lucchi, Aurelien, Orvieto, Antonio, Gorbunov, Eduard

Testo