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

preprint2026arXivOpen access

Abstract

We address the following question: given a collection {A(1),…,A(N)}\{\mathbf{A}^{(1)}, \dots, \mathbf{A}^{(N)}\} of independent d×dd \times d random matrices drawn from a common distribution P\mathbb{P}, what is the probability that the centralizer of {A(1),…,A(N)}\{\mathbf{A}^{(1)}, \dots, \mathbf{A}^{(N)}\} is trivial? We provide lower bounds on this probability in terms of the sample size NN and the dimension dd 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.

Explore this paper’s authors, topics and related work.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Reviews 0

Write a reviewWrite

No reviews yet.

Discussion 0

Add a commentWrite

No comments yet.