Skip to Main content Skip to Navigation
Preprints, Working Papers, ...

Inverse problems for structured datasets using parallel TAP equations and RBM

Abstract : We propose an efficient algorithm to solve inverse problems in the presence of binary clustered datasets. We consider the paradigmatic Hopfield model in a teacher student scenario, where this situation is found in the retrieval phase. This problem has been widely analyzed through various methods such as mean-field approaches or the pseudo-likelihood optimization. Our approach is based on the estimation of the posterior using the Thouless-Anderson-Palmer (TAP) equations in a parallel updating scheme. At the difference with other methods, it allows to retrieve the exact patterns of the teacher and the parallel update makes it possible to apply it for large system sizes. We also observe that the Approximate Message Passing (AMP) equations do not reproduce the expected behavior in the direct problem, questioning the standard practice used to obtain time indexes coming from Belief Propagation (BP). We tackle the same problem using a Restricted Boltzmann Machine (RBM) and discuss the analogies between the two algorithms.
Complete list of metadatas
Contributor : Aurélien Decelle <>
Submitted on : Friday, December 20, 2019 - 10:16:31 AM
Last modification on : Wednesday, October 14, 2020 - 4:00:42 AM

Links full text


  • HAL Id : hal-02420755, version 1
  • ARXIV : 1906.11988



Aurelien Decelle, Sungmin Hwang, Jacopo Rocchi, Daniele Tantari. Inverse problems for structured datasets using parallel TAP equations and RBM. 2019. ⟨hal-02420755⟩



Record views