Eduard Gorbunov

papers

442

total citations

papers (11)

Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping

NEURIPS 2020arXiv

146

citations

Linearly Converging Error Compensated SGD

NEURIPS 2020arXiv

citations

Last-Iterate Convergence of Optimistic Gradient Method for Monotone Variational Inequalities

NEURIPS 2022arXiv

citations

Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices

NEURIPS 2021arXiv

citations

Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise

NEURIPS 2022arXiv

citations

High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise

ICML 2024arXiv

citations

Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance

NEURIPS 2023arXiv

citations

Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions

NEURIPS 2023arXiv

citations

Eduard Gorbunov

papers (11)

Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping

Linearly Converging Error Compensated SGD

Last-Iterate Convergence of Optimistic Gradient Method for Monotone Variational Inequalities

Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices

Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise

High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise

Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance

Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions

Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum

Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed

Byzantine-Tolerant Methods for Distributed Variational Inequalities

papers (11)

Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping

Linearly Converging Error Compensated SGD

Last-Iterate Convergence of Optimistic Gradient Method for Monotone Variational Inequalities

Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices

Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise

High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise

Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance

Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions

Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum

Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed

Byzantine-Tolerant Methods for Distributed Variational Inequalities