Survey propagation at finite temperature: application to a Sourlas code as a toy model
B Wemmenhove, H J Kappen
Abstract
In this paper we investigate a finite temperature generalization of survey propagation, by applying it to the problem of finite temperature decoding of a biased finite connectivity Sourlas code for temperatures lower than the Nishimori temperature. We observe that the result is a shift of the location of the dynamical critical channel noise to larger values than the corresponding dynamical transition for belief propagation, as suggested recently by Migliorini and Saad for LDPC codes. We show how the finite temperature 1-RSB SP gives accurate results in the regime where competing approaches fail to converge or fail to recover the retrieval state.
Create a lesson
Related papers
Cell-type-specific modularity in E/I networks shapes dynamical regimes and computational capabilities
Emmanouil Giannakakis, Victor Buendía, Oleg Vinogradov et al.
Finite-width shift of the edge of chaos in deep neural networks
Arn Caesar
Neural Networks with Exciton-Polariton Waveguides
Huawen Xu, Ruiqi Bao, Lingyu Tian et al.
Optical Ceiling on Polaron Mobility in Disordered Molecular Semiconductors: Lessons from Eumelanin
Alvan Hunt
Glauber dynamics of the Sherrington--Kirkpatrick spin-glass model: a dynamical cavity method
Grzegorz Szamel
Generative diffusion in long-range correlated landscapes: Speciation cascade and the foam structure of the score
Jerome Garnier-Brun, Giulio Biroli, Marc Mézard et al.