Abstract
We propose a novel iterative estimation algorithm
for linear observation models called S-AMP. The fixed points of
S-AMP are the stationary points of the exact Gibbs free energy
under a set of (first- and second-) moment consistency constraints
in the large system limit. S-AMP extends the approximate
message-passing (AMP) algorithm to general matrix ensembles
with a well-defined large system size limit. The generalization is
based on the S-transform (in free probability) of the spectrum
of the measurement matrix. Furthermore, we show that the
optimality of S-AMP follows directly from its design rather than
from solving a separate optimization problem as done for AMP.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of 2014 IEEE Information Theory Workshop (ITW) |
| Publisher | IEEE |
| Publication date | 2014 |
| Pages | 192-196 |
| ISBN (Print) | 978-1-4799-5999-0 |
| DOIs | |
| Publication status | Published - 2014 |
| Event | 2014 IEEE Information Theory Workshop - Hobart, Australia Duration: 2 Nov 2014 → 5 Nov 2014 |
Workshop
| Workshop | 2014 IEEE Information Theory Workshop |
|---|---|
| Country/Territory | Australia |
| City | Hobart |
| Period | 02/11/2014 → 05/11/2014 |
Keywords
- Variational inference
- Free energy optimization
- Approximate message passing
- S-transform in free probability