On the complexity of PAC learning in Hilbert spaces

MaRDI QIDQ6428327zbMATH OpenFDO

Authors Sergei Chubanov

Publication date 3 March 2023

Mathematics Subject Classification ID

Computational learning theory (68Q32)

Abstract: We study the problem of binary classification from the point of view of learning convex polyhedra in Hilbert spaces, to which one can reduce any binary classification problem. The problem of learning convex polyhedra in finite-dimensional spaces is sufficiently well studied in the literature. We generalize this problem to that in a Hilbert space and propose an algorithm for learning a polyhedron which correctly classifies at least $1-varepsilon$ of the distribution, with a probability of at least $1-delta,$ where $varepsilon$ and $delta$ are given parameters. Also, as a corollary, we improve some previous bounds for polyhedral classification in finite-dimensional spaces.

This page was built for publication: On the complexity of PAC learning in Hilbert spaces

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6428327)