Skip to Main content Skip to Navigation
Journal articles

Approximate Survey Propagation for Statistical Inference

Abstract : Approximate message passing algorithm enjoyed considerable attention in the last decade. In this paper we introduce a variant of the AMP algorithm that takes into account glassy nature of the system under consideration. We coin this algorithm as the approximate survey propagation (ASP) and derive it for a class of low-rank matrix estimation problems. We derive the state evolution for the ASP algorithm and prove that it reproduces the one-step replica symmetry breaking (1RSB) fixed-point equations, well-known in physics of disordered systems. Our derivation thus gives a concrete algorithmic meaning to the 1RSB equations that is of independent interest. We characterize the performance of ASP in terms of convergence and mean-squared error as a function of the free Parisi parameter s. We conclude that when there is a model mismatch between the true generative model and the inference model, the performance of AMP rapidly degrades both in terms of MSE and of convergence, while ASP converges in a larger regime and can reach lower errors. Among other results, our analysis leads us to a striking hypothesis that whenever s (or other parameters) can be set in such a way that the Nishimori condition M = Q > 0 is restored, then the corresponding algorithm is able to reach mean-squared error as low as the Bayes-optimal error obtained when the model and its parameters are known and exactly matched in the inference procedure. Contents
Complete list of metadatas

Cited literature [58 references]  Display  Hide  Download

https://hal-cea.archives-ouvertes.fr/cea-01933008
Contributor : Emmanuelle de Laborderie <>
Submitted on : Friday, November 23, 2018 - 2:46:58 PM
Last modification on : Saturday, September 19, 2020 - 4:40:03 AM

File

approximate_survey.pdf
Files produced by the author(s)

Identifiers

Citation

Fabrizio Antenucci, Florent Krzakala, Pierfrancesco Urbani, Lenka Zdeborová. Approximate Survey Propagation for Statistical Inference. Journal of Statistical Mechanics: Theory and Experiment, IOP Publishing, 2019, 2019, pp.023401. ⟨10.1088/1742-5468/aafa7d⟩. ⟨cea-01933008⟩

Share

Metrics

Record views

312

Files downloads

726