Robustness analysis improved for complex infinite dimensional spaces
Robustness Analysis via Horofunction Compactification
Logic in Computer Science
Summary
It's hard to check how systems behave when their parameters change in complicated spaces, like those used in machine learning or control engineering. Existing methods struggle with these spaces because the usual mathematical tools don't work well. The authors use a special technique called horofunction compactification to extend these spaces into a form where robust analysis becomes easier and more precise. This approach allows better approximations and computations in spaces that were hard to handle before.
What this means in practice
- •For control engineers: Analyze robustness of infinite-dimensional control systems under parameter changes using the horofunction compactification framework.
- •For machine learning engineers: Improve verification and robustness evaluation of learning algorithms operating in infinite-dimensional spaces.
A theory result. No direct application yet.
Authors
Harrison Bennett, Amin Farjudian
Abstract
Robustness analysis plays a central role in the verification and design of computational and hybrid systems, particularly when system behaviour depends continuously on parameters subject to perturbation. Existing domain-theoretic frameworks provide a principled foundation for reasoning about such perturbations via monotone maps on lattices of closed sets. However, these frameworks face significant limitations when the underlying state space is not locally compact, as is the case for the infinite-dimensional spaces that arise in analysis, machine learning, and control theory (e.g., $\ell_p$ and $L_p$ spaces). In these settings, the lattice of closed subsets fails to be continuous, and classical compactifications either sacrifice precision or lack computable structure. We propose Gromov's horofunction compactification as a new tool for robustness analysis over a class of separable metric spaces of practical importance, including separable reflexive Banach spaces. Given a metric space $\mathbb{S}$, we show that its horofunction extension yields a compact metric space together with a Lipschitz embedding, which enables robust approximations of monotone maps via Scott-continuous maps on the compactified domain. For separable spaces, the horofunction compactification is metrizable, which provides a path toward effective domain-theoretic constructions.