Ilyas Fatkhullin
11 papers · 2021–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (16) π Conference Polyglot Β· Bronze π¬ Deep Specialist (10) π Renaissance Researcher (5)
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
Venues
Top co-authors
Research topics
Machine Learning
(11)
Optimization & Theory Β· Machine Learning
(11)
Mathematics & Optimization
(5)
Optimization
(5)
Deep Learning
(3)
Reinforcement Learning
(3)
Optimization & Theory Β· Deep Learning
(3)
Methods
(2)
Computer Science
(1)
Robotics
(1)
Applications
(1)
Capabilities
(1)
Learning Types
(1)
Systems
(1)
Keywords
error feedback
(5)
stochastic optimization
(5)
sample complexity
(4)
non-convex optimization
(4)
communication compression
(3)
stochastic gradient descent
(3)
variance reduction
(3)
distributed learning
(2)
distributed training
(2)
policy gradient
(2)
convergence rate
(2)
distributed optimization
(2)
reinforcement learning
(2)
neural network training
(1)
convergence analysis
(1)
global convergence
(1)
temporal difference learning
(1)
stochastic gradient
(1)
function approximation
(1)
gradient descent
(1)
Papers
EF21 with Bells & Whistles: Six Algorithmic Extensions of Modern Error Feedback
JMLR 2025
From Gradient Clipping to Normalization for Heavy Tailed SGD
AISTATS 2025
Safe-EF: Error Feedback for Non-smooth Constrained Optimization
ICML 2025
Taming Nonconvex Stochastic Mirror Descent with General Bregman Divergence
AISTATS 2024
Momentum Provably Improves Error Feedback!
NeurIPS 2023
Reinforcement Learning with General Utilities: Simpler Variance Reduction and Large State-Action Space
ICML 2023
Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies
ICML 2023
Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods
NeurIPS 2023
3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation
ICML 2022
Sharp Analysis of Stochastic Optimization under Global Kurdyka-Lojasiewicz Inequality
NeurIPS 2022
EF21: A New, Simpler, Theoretically Better, and Practically Faster Error Feedback
NeurIPS 2021