A general learning algorithm for functions between metric spaces

TL;DR

This paper introduces a universal learning algorithm capable of approximating functions between any two metric spaces, broadening the scope of learnable functions beyond traditional settings.

Contribution

It presents a general framework for learning functions between metric spaces, extending existing methods to more abstract and diverse spaces.

Findings

The algorithm effectively approximates functions in various metric spaces.

The approach generalizes previous learning algorithms to broader contexts.

Experimental results demonstrate the algorithm's versatility and accuracy.

Abstract

In this paper we show how to approximate ("learn") a function f, where X and Y are metric spaces.