An Expectation Propagation Perspective on Approximate Message Passing

被引:40
|
作者
Meng, Xiangming [1 ]
Wu, Sheng [2 ]
Kuang, Linling [2 ]
Lu, Jianhua [1 ]
机构
[1] Tsinghua Univ, Dept Elect Engn, Beijing 100084, Peoples R China
[2] Tsinghua Univ, Tsinghua Space Ctr, Beijing 100084, Peoples R China
关键词
Approximate message passing; compressed sensing; expectation propagation; linear mixing; GRAPHS;
D O I
10.1109/LSP.2015.2391287
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
An alternative derivation for the well-known approximate message passing (AMP) algorithm proposed by Donoho et al. is presented in this letter. Compared with the original derivation, which exploits central limit theorem and Taylor expansion to simplify belief propagation (BP), our derivation resorts to expectation propagation (EP) and the neglect of high-order terms in large system limit. This alternative derivation leads to a different yet provably equivalent form of message passing, which explicitly establishes the intrinsic connection between AMP and EP, thereby offering some new insights in the understanding and improvement of AMP.
引用
收藏
页码:1194 / 1197
页数:4
相关论文
共 50 条
  • [1] Concise Derivation for Generalized Approximate Message Passing Using Expectation Propagation
    Zou, Qiuyun
    Zhang, Haochuan
    Wen, Chao-Kai
    Jin, Shi
    Yu, Rong
    [J]. IEEE SIGNAL PROCESSING LETTERS, 2018, 25 (12) : 1835 - 1839
  • [2] DISTRIBUTED APPROXIMATE MESSAGE PASSING WITH SUMMATION PROPAGATION
    Hayakawa, Ryo
    Nakai, Ayano
    Hayashi, Kazunori
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 4104 - 4108
  • [3] Expectation-Maximization Bernoulli-Gaussian Approximate Message Passing
    Vila, Jeremy
    Schniter, Philip
    [J]. 2011 CONFERENCE RECORD OF THE FORTY-FIFTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS (ASILOMAR), 2011, : 799 - 803
  • [4] Expectation-Maximization Gaussian-Mixture Approximate Message Passing
    Vila, Jeremy P.
    Schniter, Philip
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2013, 61 (19) : 4658 - 4672
  • [5] Expectation maximization as message passing
    Dauwels, J
    Korl, S
    Loeliger, HA
    [J]. 2005 IEEE International Symposium on Information Theory (ISIT), Vols 1 and 2, 2005, : 583 - 586
  • [6] An Expectation-Maximization Approach to Tuning Generalized Vector Approximate Message Passing
    Metzler, Christopher A.
    Schniter, Philip
    Baraniuk, Richard G.
    [J]. LATENT VARIABLE ANALYSIS AND SIGNAL SEPARATION (LVA/ICA 2018), 2018, 10891 : 395 - 406
  • [7] Doped expectation propagation for low-complexity message passing based detection
    Wang, Wei
    Wang, Zhongyong
    Guo, Qinghua
    Zhang, Chuanzong
    Sun, Peng
    [J]. ELECTRONICS LETTERS, 2017, 53 (06) : 403 - 405
  • [8] Bayesian Deep Learning via Expectation Maximization and Turbo Deep Approximate Message Passing
    Xu, Wei
    Liu, An
    Zhang, Yiting
    Lau, Vincent
    [J]. IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2024, 72 : 3865 - 3878
  • [9] Vector Approximate Message Passing
    Rangan, Sundeep
    Schniter, Philip
    Fletcher, Alyson K.
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2019, 65 (10) : 6664 - 6684
  • [10] Memory Approximate Message Passing
    Liu, Lei
    Huang, Shunqi
    Kurkoski, Brian M.
    [J]. 2021 IEEE INTERNATIONAL SYMPOSIUM ON INFORMATION THEORY (ISIT), 2021, : 1379 - 1384