Presentation | 2022-01-21 [Invited Talk] Deep Learning-Aided Belief Propagation for Large Multiuser MIMO Detection Takumi Takahashi, Shinsuke Ibi, Seiichi Sampei, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | With the increasing dimensionality of wireless communication signals, low-complexity signal detection algorithms to solve large-scale linear inference problems are expected to be crucial in future wireless networks. As a low-complexity linear Bayesian detector, Gaussian belief propagation (GaBP) achieves a Bayes-optimal performance with the minimum computational complexity in the large-system limit when the observation matrix entries follow an independent and identically distributed (i.i.d.) Gaussian distribution with zero mean. However, it is difficult to make such an ideal condition hold true for linear inference problems encountered in signal processing for wireless communications, and the optimal performance is not achieved even by employing sophisticated BP-based algorithms. As a promising approach to bridge this gap between theory and engineering, deep unfolding (DU), which embeds parameters into existing iterative algorithms and optimizes them via data-driven tuning, has been gaining attention. As an example, this paper will show that the DU technique can mitigate the inconvenience caused by the difference between the actual wireless communication environments and the ideal condition when GaBP is used for uplink signal detection in large multi-user MIMO (MU-MIMO) systems. The above example is employed to describe the design of trainable algorithms, the interpretation of the algorithms after training, and the performance evaluation, and we provide the essence of integrating BP and deep learning (DL) to design a practical signal detection algorithm. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | belief propagation / deep learning / large MIMO detection / deep unfolding / data-driven tuning |
Paper # | IT2021-80,SIP2021-88,RCS2021-248 |
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) | [Invited Talk] Deep Learning-Aided Belief Propagation for Large Multiuser MIMO Detection |
Sub Title (in English) | |
Keyword(1) | belief propagation |
Keyword(2) | deep learning |
Keyword(3) | large MIMO detection |
Keyword(4) | deep unfolding |
Keyword(5) | data-driven tuning |
1st Author's Name | Takumi Takahashi |
1st Author's Affiliation | Osaka University(Osaka Univ.) |
2nd Author's Name | Shinsuke Ibi |
2nd Author's Affiliation | Doshisha University(Doshisha Univ.) |
3rd Author's Name | Seiichi Sampei |
3rd Author's Affiliation | Osaka University(Osaka Univ.) |
Date | 2022-01-21 |
Paper # | IT2021-80,SIP2021-88,RCS2021-248 |
Volume (vol) | vol.121 |
Number (no) | IT-327,SIP-328,RCS-329 |
Page | pp.pp.289-294(IT), pp.289-294(SIP), pp.289-294(RCS), |
#Pages | 6 |
Date of Issue | 2022-01-13 (IT, SIP, RCS) |