# Matrix-Free Two-to-Infinity and One-to-Two Norms Estimation

Source: [Matrix-Free Two-to-Infinity and One-to-Two Norms Estimation](<https://www.sota2.com/research/paper/68fa5dfc1e209131ce9de3d6>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-22T05:00:14.433Z

Authors: Askar Tsyganov, Evgeny Frolov, Sergey Samsonov, Maxim Rakhuba

Published: 2025-08-06T13:37:37.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.04444>)

[PDF](<https://arxiv.org/pdf/2508.04444.pdf>)