Score: 1

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

Published: August 6, 2025 | arXiv ID: 2508.04444v1

By: Askar Tsyganov , Evgeny Frolov , Sergey Samsonov and more

Potential Business Impact:

Makes AI smarter and safer from attacks.

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.

Country of Origin
🇷🇺 Russian Federation

Repos / Data Links

Page Count
16 pages

Category
Computer Science:
Machine Learning (CS)