A Theory of Diversity for Random Matrices with Applications to In-Context Learning of Schrödinger Equations

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Cole, Frank, Lu, Yulong, Sehgal, Shaurya
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912831848316928
author Cole, Frank
Lu, Yulong
Sehgal, Shaurya
author_facet Cole, Frank
Lu, Yulong
Sehgal, Shaurya
contents We address the following question: given a collection $\{\mathbf{A}^{(1)}, \dots, \mathbf{A}^{(N)}\}$ of independent $d \times d$ random matrices drawn from a common distribution $\mathbb{P}$, what is the probability that the centralizer of $\{\mathbf{A}^{(1)}, \dots, \mathbf{A}^{(N)}\}$ is trivial? We provide lower bounds on this probability in terms of the sample size $N$ and the dimension $d$ for several families of random matrices which arise from the discretization of linear Schrödinger operators with random potentials. When combined with recent work on machine learning theory, our results provide guarantees on the generalization ability of transformer-based neural networks for in-context learning of Schrödinger equations.
format Preprint
id arxiv_https___arxiv_org_abs_2601_12587
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Theory of Diversity for Random Matrices with Applications to In-Context Learning of Schrödinger Equations
Cole, Frank
Lu, Yulong
Sehgal, Shaurya
Machine Learning
We address the following question: given a collection $\{\mathbf{A}^{(1)}, \dots, \mathbf{A}^{(N)}\}$ of independent $d \times d$ random matrices drawn from a common distribution $\mathbb{P}$, what is the probability that the centralizer of $\{\mathbf{A}^{(1)}, \dots, \mathbf{A}^{(N)}\}$ is trivial? We provide lower bounds on this probability in terms of the sample size $N$ and the dimension $d$ for several families of random matrices which arise from the discretization of linear Schrödinger operators with random potentials. When combined with recent work on machine learning theory, our results provide guarantees on the generalization ability of transformer-based neural networks for in-context learning of Schrödinger equations.
title A Theory of Diversity for Random Matrices with Applications to In-Context Learning of Schrödinger Equations
topic Machine Learning
url https://arxiv.org/abs/2601.12587