Rank-one matrix estimation: analysis of algorithmic and information theoretic limits by the spatial coupling method

Abstract : Factorizing low-rank matrices is a problem with many applications in machine learning and statistics, ranging from sparse PCA to community detection and sub-matrix localization. For probabilistic models in the Bayes optimal setting, general expressions for the mutual information have been proposed using powerful heuristic statistical physics computations via the replica and cavity methods, and proven in few specific cases by a variety of methods. Here, we use the spatial coupling methodology developed in the framework of error correcting codes, to rigorously derive the mutual information for the symmetric rank-one case. We characterize the detectability phase transitions in a large set of estimation problems , where we show that there exists a gap between what currently known polynomial algorithms (in particular spectral methods and approximate message-passing) can do and what is expected information theoretically. Moreover, we show that the computational gap vanishes for the proposed spatially coupled model, a promising feature with many possible applications. Our proof technique has an interest on its own and exploits three essential ingredients: the interpolation method first introduced in statistical physics, the analysis of approximate message-passing algorithms first introduced in compressive sensing, and the theory of threshold saturation for spatially coupled systems first developed in coding theory. Our approach is very generic and can be applied to many other open problems in statistical estimation where heuristic statistical physics predictions are available.
Document type :
Preprints, Working Papers, ...
Complete list of metadatas

Cited literature [40 references]  Display  Hide  Download

https://hal-cea.archives-ouvertes.fr/cea-02009706
Contributor : Emmanuelle de Laborderie <>
Submitted on : Wednesday, February 6, 2019 - 3:12:18 PM
Last modification on : Wednesday, May 15, 2019 - 3:38:35 AM
Long-term archiving on : Tuesday, May 7, 2019 - 2:34:02 PM

File

rank-one-matrix.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : cea-02009706, version 1

Citation

Jean Barbier, Mohamad Dia, Nicolas Macris, Florent Krzakala, Lenka Zdeborova. Rank-one matrix estimation: analysis of algorithmic and information theoretic limits by the spatial coupling method. 2019. ⟨cea-02009706⟩

Share

Metrics

Record views

58

Files downloads

50