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.

MailhePlumbley13-globalsip_accepted_notice.pdf - Accepted version Manuscript

Download (129kB) | Preview


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 :
Mailhe, B
Date : 1 January 2013
DOI : 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 :
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 : 16 Jan 2019 18:43

Actions (login required)

View Item View Item


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