TY - GEN
T1 - Parallel Wavelet-based Bayesian Compressive Sensing based on Gibbs Sampling
AU - Zhou, Jian
AU - Chakrabarti, Chaitali
PY - 2018/12/31
Y1 - 2018/12/31
N2 - Bayesian compressive sensing (BCS) helps address ill-posed signal recovery problems using the Bayesian estimation framework. Gibbs sampling is a technique used in Bayesian estimation that iteratively draws samples from conditional posterior distributions. However, Gibbs sampling is inherently sequential and existing parallel implementations focus on reducing the communication between computing units at the cost of increase in recovery error. In this work, we propose a two-stage parallel coefficient update scheme for wavelet-based Bayesian compressive sensing, where the first stage approximates the real distributions of the wavelet coefficients and the second stage computes the final estimate of the coefficients. While in the first stage the parallel computing units share information with each other, in the second stage, the parallel units work independently. We propose a new coefficient update scheme that updates coefficients in both stages based on data generated a few rounds ago. Such a scheme helps in relaxing the timing constraints for communication in the first stage and computations in the second stage. We design the corresponding parallel architecture and synthesize it in 7 nm technology node. We show that in a system with 8 computing units, our method helps reduce the execution time by 17.4× compared to a sequential implementation without any increase in the signal recovery error.
AB - Bayesian compressive sensing (BCS) helps address ill-posed signal recovery problems using the Bayesian estimation framework. Gibbs sampling is a technique used in Bayesian estimation that iteratively draws samples from conditional posterior distributions. However, Gibbs sampling is inherently sequential and existing parallel implementations focus on reducing the communication between computing units at the cost of increase in recovery error. In this work, we propose a two-stage parallel coefficient update scheme for wavelet-based Bayesian compressive sensing, where the first stage approximates the real distributions of the wavelet coefficients and the second stage computes the final estimate of the coefficients. While in the first stage the parallel computing units share information with each other, in the second stage, the parallel units work independently. We propose a new coefficient update scheme that updates coefficients in both stages based on data generated a few rounds ago. Such a scheme helps in relaxing the timing constraints for communication in the first stage and computations in the second stage. We design the corresponding parallel architecture and synthesize it in 7 nm technology node. We show that in a system with 8 computing units, our method helps reduce the execution time by 17.4× compared to a sequential implementation without any increase in the signal recovery error.
KW - Bayesian compressive sensing
KW - Gibbs sampling
KW - parallel implementation
UR - http://www.scopus.com/inward/record.url?scp=85061357131&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85061357131&partnerID=8YFLogxK
U2 - 10.1109/SiPS.2018.8598375
DO - 10.1109/SiPS.2018.8598375
M3 - Conference contribution
AN - SCOPUS:85061357131
T3 - IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation
SP - 140
EP - 145
BT - Proceedings of the IEEE Workshop on Signal Processing Systems, SiPS 2018
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2018 IEEE Workshop on Signal Processing Systems, SiPS 2018
Y2 - 21 October 2018 through 24 October 2018
ER -