A Clustering Approach to Learning Sparsely Used Overcomplete Dictionaries

DOI10.1109/TIT.2016.2614684MaRDI QIDQ2979124zbMATHOpenAlexFDO

Authors Alekh Agarwal, Animashree Anandkumar, Praneeth Netrapalli

Publication date 2 May 2017

Published in IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1309.1952

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05)

Abstract: We consider the problem of learning overcomplete dictionaries in the context of sparse coding, where each sample selects a sparse subset of dictionary elements. Our main result is a strategy to approximately recover the unknown dictionary using an efficient algorithm. Our algorithm is a clustering-style procedure, where each cluster is used to estimate a dictionary element. The resulting solution can often be further cleaned up to obtain a high accuracy estimate, and we provide one simple scenario where $el{l}_1$-regularized regression can be used for such a second stage.

Cited in

(13)

• Local identifiability of \(\ell_1\)-minimization dictionary learning: a sufficient and almost necessary condition
• \((L_r,L_r,1)\)-decompositions, sparse component analysis, and the blind separation of sums of exponentials
• Applied harmonic analysis and data processing. Abstracts from the workshop held March 25--31, 2018
• Unique sharp local minimum in \(\ell_1\)-minimization complete dictionary learning
• Identifiability of complete dictionary learning
• A geometric analysis of phase retrieval
• Multilinear compressive sensing and an application to convolutional linear networks
• Combinatorial rigidity of incidence systems and application to dictionary learning
• Learning sparsely used overcomplete dictionaries via alternating minimization
• Learning semidefinite regularizers
• A general framework for Bayes structured linear models
• Low complexity regularization of linear inverse problems
• $rm K$-SVD: An Algorithm for Designing Overcomplete Dictionaries for Sparse Representation

This page was built for publication: A Clustering Approach to Learning Sparsely Used Overcomplete Dictionaries

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2979124)