← Authors

Eduard Gorbunov

35 papers · 2018–2025 · 7 conferences · across top CS/AI conferences

Achievements

🌍 Conference Polyglot (7) πŸƒ Academic Marathon (7) 🐝 Cross-Pollinator (9) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (33) 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🌈 Renaissance Researcher (6) 🀝 Dynamic Duo (16) πŸ‘‘ Triple Crown πŸ† Keyword Champion (4) πŸ”¬ Deep Specialist (25) πŸ’Ž Century Club (35) πŸ—ƒοΈ Keyword Collector (101) ⚑ Prolific Year (8) πŸ”₯ Unstoppable (8)

Conferences

NIPS (13) AISTATS (7) ICML (7) ICLR (4) COLT (2) EMNLP (1) JMLR (1)

Top co-authors

Peter Richtarik (16) Samuel HorvΓ‘th (12) Alexander Gasnikov (10) Gauthier Gidel (8) Martin Takac (6) Nicolas Loizou (5) Pavel Dvurechensky (4) Nazarii Tupitsa (4) Marina Danilova (4) Igor Sokolov (3)

Keywords

variational inequality (10) stochastic optimization (9) stochastic gradient descent (8) variance reduction (7) convergence rate (6) convex optimization (6) distributed learning (5) federated learning (5) distributed optimization (5) communication compression (4) extragradient method (4) min-max optimization (3) heavy-tailed noise (3) convergence analysis (3) error feedback (3) byzantine robustness (3) gradient clipping (3) communication efficiency (3) distributed training (3) complexity bound (2)

Papers

Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization ICLR 2025
Methods for Convex $(L_0,L_1)$-Smooth Optimization: Clipping, Acceleration, and Adaptivity ICLR 2025
EF21 with Bells & Whistles: Six Algorithmic Extensions of Modern Error Feedback JMLR 2025
Clipping Improves Adam-Norm and AdaGrad-Norm when the Noise Is Heavy-Tailed ICML 2025
High-Probability Convergence for Composite and Distributed Stochastic Minimization and Variational Inequalities with Heavy-Tailed Noise ICML 2024
Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences NIPS 2024
Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad NIPS 2024
Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton Approximations NIPS 2024
Don't Compress Gradients in Random Reshuffling: Compress Gradient Differences NIPS 2024
Low-Resource Machine Translation through the Lens of Personalized Federated Learning EMNLP 2024
Communication Compression for Byzantine Robust Learning: New Efficient Algorithms and Improved Rates AISTATS 2024
Breaking the Heavy-Tailed Noise Barrier in Stochastic Optimization Problems AISTATS 2024
Stochastic Gradient Descent-Ascent: Unified Theory and New Efficient Methods AISTATS 2023
Byzantine-Tolerant Methods for Distributed Variational Inequalities NIPS 2023
Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance NIPS 2023
Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions NIPS 2023
Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top ICLR 2023
Convergence of Proximal Point and Extragradient-Based Methods Beyond Monotonicity: the Case of Negative Comonotonicity ICML 2023
High-Probability Bounds for Stochastic Optimization and Variational Inequalities: the Case of Unbounded Variance ICML 2023
Clipped Stochastic Methods for Variational Inequalities with Heavy-Tailed Noise NIPS 2022
Last-Iterate Convergence of Optimistic Gradient Method for Monotone Variational Inequalities NIPS 2022
Stochastic Extragradient: General Analysis and Improved Rates AISTATS 2022
3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation ICML 2022
Secure Distributed Training at Scale ICML 2022
Extragradient Method: O(1/K) Last-Iterate Convergence for Monotone Variational Inequalities and Connections With Cocoercivity AISTATS 2022
MARINA: Faster Non-Convex Distributed Learning with Compression ICML 2021
Moshpit SGD: Communication-Efficient Decentralized Training on Heterogeneous Unreliable Devices NIPS 2021
Local SGD: Unified Theory and New Efficient Methods AISTATS 2021
Stochastic Optimization with Heavy-Tailed Noise via Accelerated Gradient Clipping NIPS 2020
A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent AISTATS 2020
Linearly Converging Error Compensated SGD NIPS 2020
A Stochastic Derivative Free Optimization Method with Momentum ICLR 2020
Near Optimal Methods for Minimizing Convex Functions with Lipschitz $p$-th Derivatives COLT 2019
Optimal Tensor Methods in Smooth Convex and Uniformly ConvexOptimization COLT 2019
Stochastic Spectral and Conjugate Descent Methods NIPS 2018