Результаты поиска - Gorbunov, Eduard

Distributed and Stochastic Optimization Methods with Gradient Compression and Local Steps по Gorbunov, Eduard

Полный текст
Полный текст

Unified analysis of SGD-type methods по Gorbunov, Eduard

Полный текст
Полный текст

Distributed Methods with Absolute Compression and Error Compensation по Danilova, Marina, Gorbunov, Eduard

Полный текст
Полный текст

Byzantine-Robust Loopless Stochastic Variance-Reduced Gradient по Fedin, Nikita, Gorbunov, Eduard

Полный текст
Полный текст

Last-Iterate Convergence Rate of Normalized Gradient Descent under Hölder Smoothness по Takezawa, Yuki, Gorbunov, Eduard

Полный текст
Полный текст

An Accelerated Method for Derivative-Free Smooth Stochastic Convex Optimization по Gorbunov, Eduard, Dvurechensky, Pavel, Gasnikov, Alexander

Полный текст
Полный текст

An Accelerated Directional Derivative Method for Smooth Stochastic Convex Optimization по Dvurechensky, Pavel, Gorbunov, Eduard, Gasnikov, Alexander

Полный текст
Полный текст

A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent по Gorbunov, Eduard, Hanzely, Filip, Richtárik, Peter

Полный текст
Полный текст

Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping по Gorbunov, Eduard, Danilova, Marina, Gasnikov, Alexander

Полный текст
Полный текст

Local SGD: Unified Theory and New Efficient Methods по Gorbunov, Eduard, Hanzely, Filip, Richtárik, Peter

Полный текст
Полный текст

Extragradient Method: $O(1/K)$ Last-Iterate Convergence for Monotone Variational Inequalities and Connections With Cocoercivity по Gorbunov, Eduard, Loizou, Nicolas, Gidel, Gauthier

Полный текст
Полный текст

Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions по Choudhury, Sayantan, Gorbunov, Eduard, Loizou, Nicolas

Полный текст
Полный текст

Distributed Learning with Compressed Gradient Differences по Mishchenko, Konstantin, Gorbunov, Eduard, Takáč, Martin, Richtárik, Peter

Полный текст
Полный текст

Linearly Converging Error Compensated SGD по Gorbunov, Eduard, Kovalev, Dmitry, Makarenko, Dmitry, Richtárik, Peter

Полный текст
Полный текст

MARINA: Faster Non-Convex Distributed Learning with Compression по Gorbunov, Eduard, Burlachenko, Konstantin, Li, Zhize, Richtárik, Peter

Полный текст
Полный текст

Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices по Ryabinin, Max, Gorbunov, Eduard, Plokhotnyuk, Vsevolod, Pekhimenko, Gennady

Полный текст
Полный текст

Secure Distributed Training at Scale по Gorbunov, Eduard, Borzunov, Alexander, Diskin, Michael, Ryabinin, Max

Полный текст
Полный текст

Stochastic Extragradient: General Analysis and Improved Rates по Gorbunov, Eduard, Berard, Hugo, Gidel, Gauthier, Loizou, Nicolas

Полный текст
Полный текст

Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods по Beznosikov, Aleksandr, Gorbunov, Eduard, Berard, Hugo, Loizou, Nicolas

Полный текст
Полный текст

Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top по Gorbunov, Eduard, Horváth, Samuel, Richtárik, Peter, Gidel, Gauthier

Полный текст
Полный текст