University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Dictionary Learning via Projected Maximal Exploration

Mailhe, B and Plumbley, MD (2013) Dictionary Learning via Projected Maximal Exploration In: IEEE Global Conference on Signal and Information Processing (GlobalSIP), 2013-12-03 - 2013-12-05, Austin, TX.

[img]
Preview
Text
MailhePlumbley13-globalsip_accepted_notice.pdf - Accepted version Manuscript

Download (129kB) | Preview

Abstract

This work presents a geometrical analysis of the Large Step Gradient Descent (LGD) dictionary learning algorithm. LGD updates the atoms of the dictionary using a gradient step with a step size equal to twice the optimal step size. We show that the large step gradient descent can be understood as a maximal exploration step where one goes as far away as possible without increasing the the error. We also show that the LGD iteration is monotonic when the algorithm used for the sparse approximation step is close enough to orthogonal.

Item Type: Conference or Workshop Item (Conference Paper)
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
NameEmailORCID
Mailhe, BUNSPECIFIEDUNSPECIFIED
Plumbley, MDm.plumbley@surrey.ac.ukUNSPECIFIED
Date : 1 January 2013
Identification Number : 10.1109/GlobalSIP.2013.6736963
Copyright Disclaimer : © 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Contributors :
ContributionNameEmailORCID
UNSPECIFIEDIEEE, UNSPECIFIEDUNSPECIFIED
Uncontrolled Keywords : Dictionary learning, sparse representations, global optimization, projected gradient descent
Related URLs :
Depositing User : Symplectic Elements
Date Deposited : 17 May 2017 13:21
Last Modified : 29 Nov 2017 14:00
URI: http://epubs.surrey.ac.uk/id/eprint/838867

Actions (login required)

View Item View Item

Downloads

Downloads per month over past year


Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800