activity
20212024
most cited3PC: Three Point Compressors for Communication-Efficient Distributed Training and a Better Theory for Lazy Aggregation

7 citations · 13 across the 11 of their papers we have counts for

collaborators
Showing cs.LGShow all

11 papers · 1 filter

cs.LG20241 cited

On the Convergence of DP-SGD with Adaptive Clipping

Egor Shulgin, Peter Richtárik

Stochastic Gradient Descent (SGD) with gradient clipping is a powerful technique for enabling differentially private optimization. Although prior works extensively investigated cli…

cs.LG2024

MARINA-P: Superior Performance in Non-smooth Federated Optimization with Adaptive Stepsizes

Igor Sokolov, Peter Richtárik

Non-smooth communication-efficient federated optimization is crucial for many machine learning applications, yet remains largely unexplored theoretically. Recent advancements have…

cs.LG2024

Pushing the Limits of Large Language Model Quantization via the Linearity Theorem

Vladimir Malinovskii, Andrei Panferov, Ivan Ilin +3

Quantizing large language models has become a standard way to reduce their memory and computational costs. Typically, existing methods focus on breaking down the problem into indiv…

cs.LG2024

Error Feedback under -Smoothness: Normalization and Momentum

Sarit Khirirat, Abdurakhmon Sadiev, Artem Riabinin +2

We provide the first proof of convergence for normalized error feedback algorithms across a wide range of machine learning problems. Despite their popularity and efficiency in trai…

cs.LG2024

Randomized Asymmetric Chain of LoRA: The First Meaningful Theoretical Framework for Low-Rank Adaptation

Grigory Malinovsky, Umberto Michieli, Hasan Abed Al Kader Hammoud +4

Fine-tuning has become a popular approach to adapting large foundational models to specific tasks. As the size of models and datasets grows, parameter-efficient fine-tuning techniq…

cs.LG2024

Unlocking FedNL: Self-Contained Compute-Optimized Implementation

Konstantin Burlachenko, Peter Richtárik

Federated Learning (FL) is an emerging paradigm that enables intelligent agents to collaboratively train Machine Learning (ML) models in a distributed manner, eliminating the need…