7 papers
Distance-Aware Muon: Adaptive Step Scaling for Normalized Optimization
Yury Demidovich, Abhishek Chakraborty, Grigory Malinovsky +2
Muon and related normalized optimizers decouple the choice of update direction from the choice of step scale, but their practical performance remains sensitive to the scale of the…
MAST: Model-Agnostic Sparsified Training
Yury Demidovich, Grigory Malinovsky, Egor Shulgin +1
We introduce a novel optimization problem formulation that departs from the conventional way of minimizing machine learning model loss as a black-box function. Unlike traditional f…
Better LMO-based Momentum Methods with Second-Order Information
Sarit Khirirat, Abdurakhmon Sadiev, Yury Demidovich +1
The use of momentum in stochastic optimization algorithms has shown empirical success across a range of machine learning tasks. Recently, a new class of stochastic momentum algorit…
Improved Convergence in Parameter-Agnostic Error Feedback through Momentum
Abdurakhmon Sadiev, Yury Demidovich, Igor Sokolov +3
Communication compression is essential for scalable distributed training of modern machine learning models, but it often degrades convergence due to the noise it introduces. Error…
Bernoulli-LoRA: A Theoretical Framework for Randomized Low-Rank Adaptation
Igor Sokolov, Abdurakhmon Sadiev, Yury Demidovich +2
Parameter-efficient fine-tuning (PEFT) has emerged as a crucial approach for adapting large foundational models to specific tasks, particularly as model sizes continue to grow expo…
Methods with Local Steps and Random Reshuffling for Generally Smooth Non-Convex Federated Optimization
Yury Demidovich, Petr Ostroukhov, Grigory Malinovsky +4
Non-convex Machine Learning problems typically do not adhere to the standard smoothness assumption. Based on empirical findings, Zhang et al. (2020b) proposed a more realistic gene…