King's College London

Research portal

Dictionary Learning with BLOTLESS Update

Research output: Contribution to journalArticle

Qi Yu, Wei Dai, Zoran Cvetkovic, Jubo Zhu

Original languageEnglish
Article number8985423
Pages (from-to)1635-1645
Number of pages11
JournalIEEE Transactions on Signal Processing
Volume68
Early online date6 Feb 2020
DOIs
Publication statusE-pub ahead of print - 6 Feb 2020

Documents

  • Dictionary Learning with Blotless_YU_Epub6Feb2020_GREEN AAM

    Dictionary_Learning_with_Blotless_YU_Epub8Feb2020_GREEN_AAM.pdf, 1.99 MB, application/pdf

    28/02/2020

    Accepted author manuscript

    ©2020 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.

King's Authors

Abstract

Algorithms for learning a dictionary to sparsely represent a given dataset typically alternate between sparse coding and dictionary update stages. Methods for dictionary update aim to minimise expansion error by updating dictionary vectors and expansion coefficients given patterns of non-zero coefficients obtained in the sparse coding stage. We propose a block total least squares (BLOTLESS) algorithm for dictionary update. BLOTLESS updates a block of dictionary elements and the corresponding sparse coefficients simultaneously. In the error free case, three necessary conditions for exact recovery are identified. Lower bounds on the number of training data are established so that the necessary conditions hold with high probability. Numerical simulations show that the bounds approximate well the number of training data needed for exact dictionary recovery. Numerical experiments further demonstrate several benefits of dictionary learning with BLOTLESS update compared with state-of-the-art algorithms especially when the amount of training data is small.

View graph of relations

© 2018 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454