Generalized support vector regression: duality and tensor-kernel representation

TL;DR

This paper develops a duality framework and tensor-kernel approach for support vector regression in Banach spaces, enabling new computational methods and broad kernel classes.

Contribution

It introduces a duality-based formulation and tensor-kernel representation for support vector regression in Banach spaces, overcoming previous learning difficulties.

Findings

Explicit dual problem formulation using Fenchel-Rockafellar duality.

A new computational framework based on tensor-kernels.

Application to a broad class of power series tensor kernels.

Abstract

In this paper we study the variational problem associated to support vector regression in Banach function spaces. Using the Fenchel-Rockafellar duality theory, we give explicit formulation of the dual problem as well as of the related optimality conditions. Moreover, we provide a new computational framework for solving the problem which relies on a tensor-kernel representation. This analysis overcomes the typical difficulties connected to learning in Banach spaces. We finally present a large class of tensor-kernels to which our theory fully applies: power series tensor kernels. This type of kernels describe Banach spaces of analytic functions and include generalizations of the exponential and polynomial kernels as well as, in the complex case, generalizations of the Szeg\"o and Bergman kernels.