TY - GEN
T1 - Demixing structured superposition signals from periodic and aperiodic nonlinear observations
AU - Soltani, Mohammadreza
AU - Hegde, Chinmay
N1 - Funding Information:
This work is supported in part by NSF grants CCF-1566281 and IIP-1632116 and an NVIDIA GPU grant.
Funding Information:
The first part of this manuscript appeared in the (non-archival) workshop paper [1]. This work is supported in part by NSF grants CCF-1566281 and IIP-1632116 and an NVIDIA GPU grant.
Publisher Copyright:
© 2017 IEEE.
PY - 2018/3/7
Y1 - 2018/3/7
N2 - We consider the demixing problem of two (or more) structured high-dimensional vectors from a limited number of nonlinear observations where this nonlinearity is due to either a periodic or an aperiodic function. We study certain families of structured superposition models, and propose a method which provably recovers the components given (nearly) m = O (s) samples where s denotes the sparsity level of the underlying components. This strictly improves upon previous nonlinear demixing techniques and asymptotically matches the best possible sample complexity. We also provide a range of simulations to illustrate the performance of the proposed algorithms.
AB - We consider the demixing problem of two (or more) structured high-dimensional vectors from a limited number of nonlinear observations where this nonlinearity is due to either a periodic or an aperiodic function. We study certain families of structured superposition models, and propose a method which provably recovers the components given (nearly) m = O (s) samples where s denotes the sparsity level of the underlying components. This strictly improves upon previous nonlinear demixing techniques and asymptotically matches the best possible sample complexity. We also provide a range of simulations to illustrate the performance of the proposed algorithms.
UR - http://www.scopus.com/inward/record.url?scp=85048125583&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048125583&partnerID=8YFLogxK
U2 - 10.1109/GlobalSIP.2017.8309144
DO - 10.1109/GlobalSIP.2017.8309144
M3 - Conference contribution
AN - SCOPUS:85048125583
T3 - 2017 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2017 - Proceedings
SP - 1165
EP - 1169
BT - 2017 IEEE Global Conference on Signal and Information Processing, GlobalSIP 2017 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th IEEE Global Conference on Signal and Information Processing, GlobalSIP 2017
Y2 - 14 November 2017 through 16 November 2017
ER -