- The Experience
- The Programs
- MBA Program
- MSx Program
- PhD Program
- Executive Education
- Stanford Ignite
- Research Fellows Program
- Summer Institute for General Management
- Stanford LEAD Certificate: Corporate Innovation
- Stanford Innovation & Entrepreneurship Certificate
- Executive Program for Nonprofit Leaders
- Executive Program in Social Entrepreneurship
- Executive Program for Education Leaders
- Stanford go.to.market
- Faculty & Research
- Insights
- Alumni
- Events
You are here
The dynamics of message passing on dense graphs, with applications to compressed sensing
The dynamics of message passing on dense graphs, with applications to compressed sensing
IEEE Transcations on Information Theory.
2011, Vol. 57, Issue 2, Pages 764-785
Approximate message passing algorithms proved to be extremely effective in reconstructing sparse signals from a small number of incoherent linear measurements. Extensive numerical experiments further showed that their dynamics is accurately tracked by a simple one-dimensional iteration termed state evolution. In this paper we provide the first rigorous foundation to state evolution. We prove that indeed it holds asymptotically in the large system limit for sensing matrices with independent and identically distributed gaussian entries. While our focus is on message passing algorithms for compressed sensing, the analysis extends beyond this setting, to a general class of algorithms on dense graphs. In this context, state evolution plays the role that density evolution has for sparse graphs. The proof technique is fundamentally different from thestandard approach to density evolution, in that it copes with large number of short loops in the underlying factor graph. It relies instead on a conditioning technique recently developed by Erwin Bolthausen in the context of spin glass theory.