Mher Safaryan
11 papers · 2021–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Cross-Pollinator (13) πΊοΈ Taxonomy Completionist (18) π Conference Polyglot (5)
π£
Hot Topic Early Bird
π
Century Club
(11)
π₯
Unstoppable
(5)
Conferences
NIPS (5)
AISTATS (2)
ICML (2)
ICLR (1)
JMLR (1)
Top co-authors
Keywords
distributed optimization
(4)
stochastic gradient descent
(3)
model compression
(3)
federated learning
(2)
communication efficiency
(2)
non-convex optimization
(2)
second-order optimization
(2)
gradient compression
(2)
distributed learning
(2)
communication compression
(2)
convergence analysis
(2)
distributed training
(1)
variance reduction
(1)
neural network optimization
(1)
sparse recovery
(1)
adaptive optimization
(1)
convergence guarantee
(1)
linear convergence
(1)
knowledge distillation
(1)
stochastic gradient
(1)
Papers
LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics
ICLR 2025
AsGrad: A Sharp Unified Analysis of Asynchronous-SGD Algorithms
AISTATS 2024
MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence
NIPS 2024
The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information
NIPS 2024
Knowledge Distillation Performs Partial Variance Reduction
NIPS 2023
On Biased Compression for Distributed Learning
JMLR 2023
Basis Matters: Better Communication-Efficient Second Order Methods for Federated Learning
AISTATS 2022
Theoretically Better and Numerically Faster Distributed Optimization with Smoothness-Aware Quantization Techniques
NIPS 2022
FedNL: Making Newton-Type Methods Applicable to Federated Learning
ICML 2022
Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization
NIPS 2021
Stochastic Sign Descent Methods: New Algorithms and Better Theory
ICML 2021