Elnur Gasanov
7 papers · 2018–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+4 more ↓ Show less ↑
π£ Hot Topic Early Bird π§ Keyword Pioneer π Conference Polyglot (4) π Academic Marathon (6) π Cross-Pollinator (12)
π
Renaissance Researcher
(5)
πΊοΈ
Taxonomy Completionist
(15)
π
Interdisciplinary Bridge
π
Keyword Champion
(2)
Conferences
AISTATS (2)
ICML (2)
NIPS (2)
ICLR (1)
Top co-authors
Keywords
distributed optimization
(2)
coordinate descent
(2)
communication efficiency
(2)
randomized coordinate descent
(2)
stochastic optimization
(2)
federated learning
(2)
decentralized optimization
(1)
strong convexity
(1)
distributed training
(1)
complexity analysis
(1)
conjugate gradient
(1)
network optimization
(1)
strongly convex optimization
(1)
linear convergence
(1)
condition number
(1)
randomized algorithm
(1)
spectral method
(1)
gradient compression
(1)
lower bound
(1)
generative adversarial network
(1)
Papers
Understanding Progressive Training Through the Framework of Randomized Coordinate Descent
AISTATS 2024
Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness Constants
ICLR 2024
FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning
AISTATS 2022
3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation
ICML 2022
Lower Bounds and Optimal Algorithms for Smooth and Strongly Convex Decentralized Optimization Over Time-Varying Networks
NIPS 2021
From Local SGD to Local Fixed-Point Methods for Federated Learning
ICML 2020
Stochastic Spectral and Conjugate Descent Methods
NIPS 2018