Presentation 2021-08-23
[Invited Talk] Block-Sparse Estimation using Optimal Block Structure
Hiroki Kuroda,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This talk presents a convex optimization based block-sparse estimation method which is effective even when concrete block partitions are not available. For the estimation of a block-sparse signal whose block partition is known a priori, extensive researches show the effectiveness of the mixed l2/l1 regularization. However, when the block partition used in the mixed l2/l1 regularization is different from that of the target signal, its estimation accuracy degrades significantly. To resolve this difficulty, the authors introduced a penalty function which takes the minimum of the mixed l2/l1 norm over all possible block partitions, and proposed its suitable convex relaxation. For the proposed regularization model, we developed an iterative algorithm which is guaranteed to converge to a globally optimal solution. In this talk, the authors' methodis described after a brief review on the existing literatures on block-sparse estimation problems.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) block-sparsity / unknown structure / regularization / convex optimization / proximal splitting algorithm
Paper # SIP2021-29
Date of Issue 2021-08-16 (SIP)

Conference Information
Committee SIP
Conference Date 2021/8/23(2days)
Place (in Japanese) (See Japanese page)
Place (in English) Online
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yukihiro Bandou(NTT)
Vice Chair Toshihisa Tanaka(Tokyo Univ. Agri.&Tech.) / Takayuki Nakachi(Ryukyu Univ.)
Secretary Toshihisa Tanaka(Xiaomi) / Takayuki Nakachi(Takushoku Univ.)
Assistant Taichi Yoshida(UEC) / Seisuke Kyochi(Univ. of Kitakyushu)

Paper Information
Registration To Technical Committee on Signal Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) [Invited Talk] Block-Sparse Estimation using Optimal Block Structure
Sub Title (in English)
Keyword(1) block-sparsity
Keyword(2) unknown structure
Keyword(3) regularization
Keyword(4) convex optimization
Keyword(5) proximal splitting algorithm
1st Author's Name Hiroki Kuroda
1st Author's Affiliation Ritsumeikan University(Ritsumeikan Univ.)
Date 2021-08-23
Paper # SIP2021-29
Volume (vol) vol.121
Number (no) SIP-144
Page pp.pp.11-11(SIP),
#Pages 1
Date of Issue 2021-08-16 (SIP)