A numerical algorithm for attaining the Chebyshev bound in optimal learning
This provides a solution for optimal function recovery in machine learning, though it appears incremental as it extends existing methods for convex semi-infinite problems.
The authors tackled the Chebyshev center problem for optimal learning from finite data by developing a numerically tractable algorithm to compute the Chebyshev radius and center for compact hypothesis spaces, demonstrating its effectiveness through numerical examples.
Given a compact subset of a Banach space, the Chebyshev center problem consists of finding a minimal circumscribing ball containing the set. In this article we establish a numerically tractable algorithm for solving the Chebyshev center problem in the context of optimal learning from a finite set of data points. For a hypothesis space realized as a compact but not necessarily convex subset of a finite-dimensional subspace of some underlying Banach space, this algorithm computes the Chebyshev radius and the Chebyshev center of the hypothesis space, thereby solving the problem of optimal recovery of functions from data. The algorithm itself is based on, and significantly extends, recent results for near-optimal solutions of convex semi-infinite problems by means of targeted sampling, and it is of independent interest. Several examples of numerical computations of Chebyshev centers are included in order to illustrate the effectiveness of the algorithm.