activity
20202026
most citedSmoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization

2 citations · 4 across the 6 of their papers we have counts for

collaborators

11 papers

cs.LG2026

Towards Robust Scaling Laws for Optimizers

Alexandra Volkova, Mher Safaryan, Christoph H. Lampert +1

The quality of Large Language Model (LLM) pretraining depends on multiple factors, including the compute budget and the choice of optimization algorithm. Empirical scaling laws are…

cs.LG2025

MT-DAO: Multi-Timescale Distributed Adaptive Optimizers with Local Updates

Alex Iacob, Andrej Jovanovic, Mher Safaryan +6

Training large models with distributed data parallelism (DDP) requires frequent communication of gradients across workers, which can saturate bandwidth. Infrequent communication st…

cs.LG2025

Unified Scaling Laws for Compressed Representations

Andrei Panferov, Alexandra Volkova, Ionut-Vlad Modoranu +3

Scaling laws have shaped recent advances in machine learning by enabling predictable scaling of model performance based on model size, computation, and data volume. Concurrently, t…

cs.LG2025

DES-LOC: Desynced Low Communication Adaptive Optimizers for Training Foundation Models

Alex Iacob, Lorenzo Sani, Mher Safaryan +8

Scaling foundation model training with Distributed Data Parallel (DDP) methods is bandwidth-limited. Existing infrequent communication methods like Local SGD were designed to synch…

cs.LG2025

FFT-based Dynamic Subspace Selection for Low-Rank Adaptive Optimization of Large Language Models

Ionut-Vlad Modoranu, Mher Safaryan, Erik Schultheis +3

Low-rank optimization has emerged as a promising direction in training large language models (LLMs) to improve running time and reduce the memory usage of adaptive optimizers by co…

cs.LG2024

LDAdam: Adaptive Optimization from Low-Dimensional Gradient Statistics

Thomas Robert, Mher Safaryan, Ionut-Vlad Modoranu +1

We introduce LDAdam, a memory-efficient optimizer for training large models, that performs adaptive optimization steps within lower dimensional subspaces, while consistently explor…