Phase Transitions and Sample Complexity in Bayes-Optimal Matrix Factorization

DOI10.1109/TIT.2016.2556702zbMath1359.94109arXiv1402.1298OpenAlexW1959879694WikidataQ59460042 ScholiaQ59460042MaRDI QIDQ2976727

Marc Mézard, Ayaka Sakata, Lenka Zdeborová, Yoshiyuki Kabashima, Florent Krzakala

Publication date: 28 April 2017

Published in: IEEE Transactions on Information Theory (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1402.1298

Mathematics Subject Classification ID

Signal theory (characterization, reconstruction, filtering, etc.) (94A12)

Related Items

Approximate message passing with spectral initialization for generalized linear models*, Mean-field inference methods for neural networks, Estimation of low-rank matrices via approximate message passing, Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising, Generalized TAP Free Energy, Fundamental limits of weak recovery with applications to phase retrieval, The decimation scheme for symmetric matrix factorization, On the TAP equations via the cavity approach in the generic mixed \(p\)-spin models, Constrained low-rank matrix estimation: phase transitions, approximate message passing and applications, Non-convex multi-species Hopfield models, Universality of approximate message passing algorithms, Approximate method of variational Bayesian matrix factorization/completion with sparse prior, Generalized approximate survey propagation for high-dimensional estimation ^*, A Unifying Tutorial on Approximate Message Passing, Approximate matrix completion based on cavity method, Prediction errors for penalized regressions based on generalized approximate message passing