Eduard Gorbunov

Assistant Professor@Mohamed bin Zayed University of Artificial Intelligence·阿联酋·OpenReview

研究方向

optimization · machine learning · stochastic optimization · distributed optimization · derivative-free optimization · federated learning · variational inequalities · min-max problems

Eduard Gorbunov

Exponential Objective Decrease in Convex Setup is Possible! Gradient Descent Method Variants under $(L_0,L_1)$-Smoothness

Convergence of Clipped-SGD for Convex $(L_0,L_1)$-Smooth Optimization with Heavy-Tailed Noise

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

On the Interaction of Batch Noise, Adaptivity, and Compression, under $(L_0,L_1)$-Smoothness: An SDE Approach

Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning

Selective Collaboration for Robust Federated Learning

High-Probability Bounds for the Last Iterate of Clipped SGD

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

Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization

Differentially Private Clipped-SGD: High-Probability Convergence with Arbitrary Clipping Level

Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity

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

Median Clipping for Zeroth-order Non-Smooth Convex Optimization and Multi Arm Bandit Problem with Heavy-tailed Symmetric Noise

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

Communication-efficient Algorithms Under Generalized Smoothness Assumptions

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

Federated Learning Can Find Friends That Are Advantageous