Presentation | 2022-01-21 Deep-Unfolded Sparse Signal Recovery Algorithm using TopK Operator Masanari Mizutani, Satoshi Takabe, Tadashi Wadayama, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Compressed sensing for estimating sparse signals is formulated as an NP-hard problem, where LASSO based on convex relaxation is usually solved alternatively. A drawback of LASSO-based methods is that prior information on sparsity $k$ of an original vector is directly unavailable. In this paper, we present a projected gradient descent-like algorithm called TopK-ISTA using an approximate projection operator called TopK operator, which iteratively searches a solution using the sparsity $k$ directly. In addition, we propose a trainable algorithm by combining TopK-ISTA with the notion of deep unfolding, in which internal parameters of the algorithm can be learned using training data. We also evaluate its signal recovery performance by comparing some existing methods. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | compressed sensing / approximate projection / projected gradient descent / deep unfolding |
Paper # | IT2021-72,SIP2021-80,RCS2021-240 |
Date of Issue | 2022-01-13 (IT, SIP, RCS) |
Conference Information | |
Committee | RCS / SIP / IT |
---|---|
Conference Date | 2022/1/20(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Online |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Eiji Okamoto(Nagoya Inst. of Tech.) / Yukihiro Bandou(NTT) / Tadashi Wadayama(Nagoya Inst. of Tech.) |
Vice Chair | Toshihiko Nishimura(Hokkaido Univ.) / Tomoya Tandai(Toshiba) / Fumihide Kojima(NICT) / Toshihisa Tanaka(Tokyo Univ. Agri.&Tech.) / Takayuki Nakachi(Ryukyu Univ.) / Tetsuya Kojima(Tokyo Kosen) |
Secretary | Toshihiko Nishimura(NEC) / Tomoya Tandai(Panasonic) / Fumihide Kojima(Xiaomi) / Toshihisa Tanaka(Takushoku Univ.) / Takayuki Nakachi(Tokyo Univ. Agri.&Tech.) / Tetsuya Kojima(Saitamai Univ.) |
Assistant | Koichi Adachi(Univ. of Electro-Comm.) / Osamu Nakamura(Sharp) / Manabu Sakai(Mitsubishi Electric) / Masashi Iwabuchi(NTT) / Tatsuki Okuyama(NTT DOCOMO) / Taichi Yoshida(UEC) / Seisuke Kyochi(Univ. of Kitakyushu) / Masanori Hirotomo(Saga Univ.) |
Paper Information | |
Registration To | Technical Committee on Radio Communication Systems / Technical Committee on Signal Processing / Technical Committee on Information Theory |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Deep-Unfolded Sparse Signal Recovery Algorithm using TopK Operator |
Sub Title (in English) | |
Keyword(1) | compressed sensing |
Keyword(2) | approximate projection |
Keyword(3) | projected gradient descent |
Keyword(4) | deep unfolding |
1st Author's Name | Masanari Mizutani |
1st Author's Affiliation | Nagoya Institute of Technology(NITech) |
2nd Author's Name | Satoshi Takabe |
2nd Author's Affiliation | Tokyo Institute of Technology(TITech) |
3rd Author's Name | Tadashi Wadayama |
3rd Author's Affiliation | Nagoya Institute of Technology(NITech) |
Date | 2022-01-21 |
Paper # | IT2021-72,SIP2021-80,RCS2021-240 |
Volume (vol) | vol.121 |
Number (no) | IT-327,SIP-328,RCS-329 |
Page | pp.pp.245-251(IT), pp.245-251(SIP), pp.245-251(RCS), |
#Pages | 7 |
Date of Issue | 2022-01-13 (IT, SIP, RCS) |