Grigory Malinovsky
12 papers · 2022–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
π Conference Polyglot (6) π Interdisciplinary Bridge π§ Keyword Pioneer π£ Hot Topic Early Bird π Cross-Pollinator (13)
π
Cross-Pollinator
(13)
π€
Dynamic Duo
(11)
π
Grand Slam
π
Keyword Champion
(2)
β
The Questioner
π
Century Club
(12)
Conferences
NIPS (5)
ICLR (2)
UAI (2)
AAAI (1)
AISTATS (1)
ICML (1)
Top co-authors
Keywords
federated learning
(5)
stochastic optimization
(4)
variance reduction
(4)
stochastic gradient descent
(3)
distributed optimization
(2)
communication complexity
(2)
gradient compression
(2)
neural network optimization
(2)
random reshuffling
(2)
client sampling
(2)
local training
(2)
communication efficiency
(2)
convergence guarantee
(2)
derivative-free optimization
(1)
nonsmooth optimization
(1)
distributed training
(1)
convergence analysis
(1)
adaptive optimization
(1)
proximal gradient descent
(1)
proximal gradient
(1)
Papers
Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization
ICLR 2025
MAST: model-agnostic sparsified training
ICLR 2025
An Optimal Algorithm for Strongly Convex Min-Min Optimization
UAI 2025
Minibatch Stochastic Three Points Method for Unconstrained Smooth Minimization
AAAI 2024
Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
NIPS 2024
MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence
NIPS 2024
Don't Compress Gradients in Random Reshuffling: Compress Gradient Differences
NIPS 2024
Can 5th Generation Local Training Methods Support Client Sampling? Yes!
AISTATS 2023
A Guide Through the Zoo of Biased SGD
NIPS 2023
Random Reshuffling with Variance Reduction: New Analysis and Better Rates
UAI 2023
Variance Reduced ProxSkip: Algorithm, Theory and Application to Federated Learning
NIPS 2022
ProxSkip: Yes! Local Gradient Steps Provably Lead to Communication Acceleration! Finally!
ICML 2022