Consistency Analysis of Spectral Regularization Algorithms

Consistency Analysis of Spectral Regularization Algorithms

We investigate the consistency of spectral regularization algorithms. We generalize the usual definition of regularization function to enrich the content of spectral regularization algorithms. Under a more general prior condition, using refined error decompositions and techniques of operator norm es...

Full description

Bibliographic Details
Main Authors: Yukui Zhu, Hongwei Sun
Format: Article
Language:English
Published: Hindawi Limited 2012-01-01
Series:Abstract and Applied Analysis
Online Access:http://dx.doi.org/10.1155/2012/436510
id doaj-c484292acfd64c0e83dd324da1c99f1d
record_format Article
spelling doaj-c484292acfd64c0e83dd324da1c99f1d2020-11-25T00:10:16ZengHindawi LimitedAbstract and Applied Analysis1085-33751687-04092012-01-01201210.1155/2012/436510436510Consistency Analysis of Spectral Regularization AlgorithmsYukui Zhu0Hongwei Sun1Shandong Provincial Key Laboratory of Network based Intelligent Computing, School of Mathematic Science, University of Jinan, Jinan 250022, ChinaShandong Provincial Key Laboratory of Network based Intelligent Computing, School of Mathematic Science, University of Jinan, Jinan 250022, ChinaWe investigate the consistency of spectral regularization algorithms. We generalize the usual definition of regularization function to enrich the content of spectral regularization algorithms. Under a more general prior condition, using refined error decompositions and techniques of operator norm estimation, satisfactory error bounds and learning rates are proved.http://dx.doi.org/10.1155/2012/436510
collection DOAJ
language English
format Article
sources DOAJ
author Yukui Zhu
Hongwei Sun
spellingShingle Yukui Zhu
Hongwei Sun
Consistency Analysis of Spectral Regularization Algorithms
Abstract and Applied Analysis
author_facet Yukui Zhu
Hongwei Sun
author_sort Yukui Zhu
title Consistency Analysis of Spectral Regularization Algorithms
title_short Consistency Analysis of Spectral Regularization Algorithms
title_full Consistency Analysis of Spectral Regularization Algorithms
title_fullStr Consistency Analysis of Spectral Regularization Algorithms
title_full_unstemmed Consistency Analysis of Spectral Regularization Algorithms
title_sort consistency analysis of spectral regularization algorithms
publisher Hindawi Limited
series Abstract and Applied Analysis
issn 1085-3375
1687-0409
publishDate 2012-01-01
description We investigate the consistency of spectral regularization algorithms. We generalize the usual definition of regularization function to enrich the content of spectral regularization algorithms. Under a more general prior condition, using refined error decompositions and techniques of operator norm estimation, satisfactory error bounds and learning rates are proved.
url http://dx.doi.org/10.1155/2012/436510
work_keys_str_mv AT yukuizhu consistencyanalysisofspectralregularizationalgorithms
AT hongweisun consistencyanalysisofspectralregularizationalgorithms
_version_ 1725408523828854784

Similar Items