collaborators

18 papers

cs.DS2026

The matrix-vector complexity of

Michał Dereziński, Ethan N. Epperly, Raphael A. Meyer

Matrix--vector algorithms, particularly Krylov subspace methods, are widely viewed as the most effective algorithms for solving large systems of linear equations. This paper establ…

cs.LG2026

How AI settled the complexity of the oldest SGD algorithm

Michał Dereziński, Xiaoyu Dong

In 1937, Stefan Kaczmarz proposed a simple algorithm for solving systems of linear equations. This algorithm turned out to be the earliest known example of stochastic gradient desc…

math.NA2026

Towards Universal Convergence of Backward Error in Linear System Solvers

Michał Dereziński, Yuji Nakatsukasa, Elizaveta Rebrova

The quest for an algorithm that solves an linear system in time complexity, or when solving up to relative error, is a long-sta…

cs.LG2026

Perfect Parallelization in Mini-Batch SGD with Classical Momentum Acceleration

Sachin Garg, Michał Dereziński

Accelerating stochastic gradient methods with classical momentum schemes, such as Polyak's heavy ball, has proven highly successful in training large-scale machine learning models,…

math.NA2026

Numerical Instabilities in the Kaczmarz Method and Stabilization by Iterative Refinement

Michał Dereziński, Ethan N. Epperly, Deanna Needell +1

The randomized Kaczmarz method and its accelerated variants are a powerful class of iterative methods for solving large-scale linear systems, offering guaranteed convergence with l…

math.NA2026

Accelerating Power Method with Fast Sketching for Stronger Low-Rank Approximation

Shabarish Chenakkod, Michał Dereziński

The power method is one of the most fundamental tools for extracting top principal components from data through low-rank matrix approximation. Yet, when the target rank is large, t…