Alternative to extended block sparse Bayesian learning and its relation to pattern-coupled sparse Bayesian learning
We consider the problem of recovering block sparse signals with unknown block partition and propose a better alternative to the extended block sparse Bayesian learning (EBSBL). The underlying relationship between the proposed method EBSBL and pattern-coupled sparse Bayesian learning (PC-SBL) is expl...
| Үндсэн зохиолчид: | , , , |
|---|---|
| Бусад зохиолчид: | |
| Формат: | Journal Article |
| Хэл сонгох: | English |
| Хэвлэсэн: |
2020
|
| Нөхцлүүд: | |
| Онлайн хандалт: | https://hdl.handle.net/10356/139369 |
| _version_ | 1826115138103541760 |
|---|---|
| author | Wang, Lu Zhao, Lifan Rahardja, Susanto Bi, Guoan |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Wang, Lu Zhao, Lifan Rahardja, Susanto Bi, Guoan |
| author_sort | Wang, Lu |
| collection | NTU |
| description | We consider the problem of recovering block sparse signals with unknown block partition and propose a better alternative to the extended block sparse Bayesian learning (EBSBL). The underlying relationship between the proposed method EBSBL and pattern-coupled sparse Bayesian learning (PC-SBL) is explicitly revealed. The proposed method adopts a cluster-structured prior for sparse coefficients, which encourages dependencies among neighboring coefficients by properly manipulating the hyperparameters of the neighborhood. Due to entanglement of the hyperparameters, a joint sparsity assumption is made to yield a suboptimal analytic solution. The alternative algorithm avoids high dictionary coherence in EBSBL, reduces the unknowns of EBSBL, and explains the effectiveness of EBSBL. The proposed algorithm also avoids the vulnerability of parameter choice in PC-SBL. Results of comprehensive simulations demonstrate that the proposed algorithm achieves performance that is close to the best performance of PC-SBL. In addition, it outperforms EBSBL and other recently reported algorithms particularly under noisy and low sampling scenarios. |
| first_indexed | 2024-10-01T03:50:38Z |
| format | Journal Article |
| id | ntu-10356/139369 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2024-10-01T03:50:38Z |
| publishDate | 2020 |
| record_format | dspace |
| spelling | ntu-10356/1393692020-05-19T05:26:50Z Alternative to extended block sparse Bayesian learning and its relation to pattern-coupled sparse Bayesian learning Wang, Lu Zhao, Lifan Rahardja, Susanto Bi, Guoan School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering Block-sparse Signal Recovery Sparse Bayesian Learning (SBL) We consider the problem of recovering block sparse signals with unknown block partition and propose a better alternative to the extended block sparse Bayesian learning (EBSBL). The underlying relationship between the proposed method EBSBL and pattern-coupled sparse Bayesian learning (PC-SBL) is explicitly revealed. The proposed method adopts a cluster-structured prior for sparse coefficients, which encourages dependencies among neighboring coefficients by properly manipulating the hyperparameters of the neighborhood. Due to entanglement of the hyperparameters, a joint sparsity assumption is made to yield a suboptimal analytic solution. The alternative algorithm avoids high dictionary coherence in EBSBL, reduces the unknowns of EBSBL, and explains the effectiveness of EBSBL. The proposed algorithm also avoids the vulnerability of parameter choice in PC-SBL. Results of comprehensive simulations demonstrate that the proposed algorithm achieves performance that is close to the best performance of PC-SBL. In addition, it outperforms EBSBL and other recently reported algorithms particularly under noisy and low sampling scenarios. 2020-05-19T05:26:50Z 2020-05-19T05:26:50Z 2018 Journal Article Wang, L., Zhao, L., Rahardja, S., & Bi, G. (2018). Alternative to extended block sparse Bayesian learning and its relation to pattern-coupled sparse Bayesian learning. IEEE Transactions on Signal Processing, 66(10), 2759-2771. doi:10.1109/tsp.2018.2816574 1053-587X https://hdl.handle.net/10356/139369 10.1109/TSP.2018.2816574 2-s2.0-85044078803 10 66 2759 2771 en IEEE Transactions on Signal Processing © 2018 IEEE. All rights reserved. |
| spellingShingle | Engineering::Electrical and electronic engineering Block-sparse Signal Recovery Sparse Bayesian Learning (SBL) Wang, Lu Zhao, Lifan Rahardja, Susanto Bi, Guoan Alternative to extended block sparse Bayesian learning and its relation to pattern-coupled sparse Bayesian learning |
| title | Alternative to extended block sparse Bayesian learning and its relation to pattern-coupled sparse Bayesian learning |
| title_full | Alternative to extended block sparse Bayesian learning and its relation to pattern-coupled sparse Bayesian learning |
| title_fullStr | Alternative to extended block sparse Bayesian learning and its relation to pattern-coupled sparse Bayesian learning |
| title_full_unstemmed | Alternative to extended block sparse Bayesian learning and its relation to pattern-coupled sparse Bayesian learning |
| title_short | Alternative to extended block sparse Bayesian learning and its relation to pattern-coupled sparse Bayesian learning |
| title_sort | alternative to extended block sparse bayesian learning and its relation to pattern coupled sparse bayesian learning |
| topic | Engineering::Electrical and electronic engineering Block-sparse Signal Recovery Sparse Bayesian Learning (SBL) |
| url | https://hdl.handle.net/10356/139369 |
| work_keys_str_mv | AT wanglu alternativetoextendedblocksparsebayesianlearninganditsrelationtopatterncoupledsparsebayesianlearning AT zhaolifan alternativetoextendedblocksparsebayesianlearninganditsrelationtopatterncoupledsparsebayesianlearning AT rahardjasusanto alternativetoextendedblocksparsebayesianlearninganditsrelationtopatterncoupledsparsebayesianlearning AT biguoan alternativetoextendedblocksparsebayesianlearninganditsrelationtopatterncoupledsparsebayesianlearning |