Use this URL to cite or link to this record in EThOS: https://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.746932
Title: Structured sparsity via optimal interpolation norms
Author: McDonald, Andrew Michael
ISNI:       0000 0004 7227 3657
Awarding Body: UCL (University College London)
Current Institution: University College London (University of London)
Date of Award: 2017
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
Abstract:
We study norms that can be used as penalties in machine learning problems. In particular, we consider norms that are defined by an optimal interpolation problem and whose additional structure can be used to encourage specific characteristics, such as sparsity, in the solution to a learning problem. We first study a norm that is defined as an infimum of quadratics parameterized over a convex set. We show that this formulation includes the k-support norm for sparse vector learning, and its Moreau envelope, the box-norm. These extend naturally to spectral regularizers for matrices, and we introduce the spectral k-support norm and spectral box-norm. We study their properties and we apply the penalties to low rank matrix and multitask learning problems. We next introduce two generalizations of the k-support norm. The first of these is the (k, p)-support norm. In the matrix setting, the additional parameter p allows us to better learn the curvature of the spectrum of the underlying solution. A second application is to multilinear algebra. By considering the rank of its matricizations, we obtain a k-support norm that can be applied to learn a low rank tensor. For each of these norms we provide an optimization method to solve the underlying learning problem, and we present numerical experiments. Finally, we present a general framework for optimal interpolation norms. We focus on a specific formulation that involves an infimal convolution coupled with a linear operator, and which captures several of the penalties discussed in this thesis. Finally we introduce an algorithm to solve regularization problems with norms of this type, and we provide numerical experiments to illustrate the method.
Supervisor: Not available Sponsor: Not available
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.746932  DOI: Not available
Share: