Matrix-Free Two-to-Infinity and One-to-Two Norms Estimation
Machine Learning
2026-01-21 v2 Numerical Analysis
Numerical Analysis
Machine Learning
Abstract
In this paper, we propose new randomized algorithms for estimating the two-to-infinity and one-to-two norms in a matrix-free setting, using only matrix-vector multiplications. Our methods are based on appropriate modifications of Hutchinson's diagonal estimator and its Hutch++ version. We provide oracle complexity bounds for both modifications. We further illustrate the practical utility of our algorithms for Jacobian-based regularization in deep neural network training on image classification tasks. We also demonstrate that our methodology can be applied to mitigate the effect of adversarial attacks in the domain of recommender systems.
Cite
@article{arxiv.2508.04444,
title = {Matrix-Free Two-to-Infinity and One-to-Two Norms Estimation},
author = {Askar Tsyganov and Evgeny Frolov and Sergey Samsonov and Maxim Rakhuba},
journal= {arXiv preprint arXiv:2508.04444},
year = {2026}
}
Comments
AAAI-2026, camera-ready version