Ahmed Khaled
10 papers · 2020–2024 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π£ Hot Topic Early Bird πΊοΈ Taxonomy Completionist (19) π Interdisciplinary Bridge π§ Keyword Pioneer π Conference Polyglot (4)
π
Cross-Pollinator
(12)
π
Keyword Champion
(2)
π
Century Club
(10)
Conferences
NIPS (5)
AISTATS (2)
ICML (2)
ICLR (1)
Top co-authors
Keywords
convex optimization
(4)
stochastic gradient descent
(4)
random reshuffling
(3)
federated learning
(3)
convergence rate
(2)
gradient descent
(2)
variance reduction
(2)
communication efficiency
(2)
deep learning
(1)
distributed optimization
(1)
neural network optimization
(1)
step-size adaptation
(1)
directional smoothness
(1)
strongly convex
(1)
strong convexity
(1)
distributed training
(1)
path-dependent rate
(1)
proximal operator
(1)
nonconvex optimization
(1)
gradient compression
(1)
Papers
Don't Compress Gradients in Random Reshuffling: Compress Gradient Differences
NIPS 2024
Tuning-Free Stochastic Optimization
ICML 2024
The Road Less Scheduled
NIPS 2024
Directional Smoothness and Gradient Methods: Convergence and Adaptivity
NIPS 2024
Faster federated optimization under second-order similarity
ICLR 2023
DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method
NIPS 2023
FLIX: A Simple and Communication-Efficient Alternative to Local Methods in Federated Learning
AISTATS 2022
Proximal and Federated Random Reshuffling
ICML 2022
Tighter Theory for Local SGD on Identical and Heterogeneous Data
AISTATS 2020
Random Reshuffling: Simple Analysis with Vast Improvements
NIPS 2020