Presentation 2008-06-26
Incremental Adaptive Filtering Over Distributed Networks Using Parallel Projection Onto Hyperslabs
Noriyuki TAKAHASHI, Isao YAMADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents adaptive incremental algorithms using the metric projections onto closed hyperslabs for adaptive estimation problem over distributed networks. Our approach is to minimize the sum of mean distances to closed hyperslabs that are highly expected to contain an unknown parameter by using the incremental subgradient projection method, which we have recently developed to minimize the sum of convex functions. The proposed adaptive algorithms are then derived as stochastic approximations of this method. A numerical example shows the fast convergence of the proposed algorithms.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Adaptive network / consensus / incremental algorithm / hyperslab / projection / distributed processing
Paper # CAS2008-4,VLD2008-17,SIP2008-38
Date of Issue

Conference Information
Committee VLD
Conference Date 2008/6/19(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To VLSI Design Technologies (VLD)
Language ENG
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Incremental Adaptive Filtering Over Distributed Networks Using Parallel Projection Onto Hyperslabs
Sub Title (in English)
Keyword(1) Adaptive network
Keyword(2) consensus
Keyword(3) incremental algorithm
Keyword(4) hyperslab
Keyword(5) projection
Keyword(6) distributed processing
1st Author's Name Noriyuki TAKAHASHI
1st Author's Affiliation Department of Communications and Integrated Systems, Tokyo Institute of Technology()
2nd Author's Name Isao YAMADA
2nd Author's Affiliation Department of Communications and Integrated Systems, Tokyo Institute of Technology
Date 2008-06-26
Paper # CAS2008-4,VLD2008-17,SIP2008-38
Volume (vol) vol.108
Number (no) 106
Page pp.pp.-
#Pages 6
Date of Issue