We consider a broad class of Approximate Message Passing (AMP) algorithms defined as a Lipschitzian functional iteration in terms of an n × n random symmetric matrix A. We establish universality in noise for this AMP in the n-limit and validate this behavior in a number of AMPs popularly adapted in compressed sensing, statistical inferences, and optimizations in spin glasses.
Bibliographical noteFunding Information:
*University of Minnesota. Partially supported by NSF grant DMS-17-52184. E-mail: firstname.lastname@example.org †University of Minnesota. E-mail: email@example.com
© 2021, Institute of Mathematical Statistics. All rights reserved.
- Message passing
- Spike recovery
- Spiked random matrix