An iterative construction of solutions of the TAP equations for the Sherrington-Kirkpatrick model

From MaRDI portal
Publication:393708


DOI10.1007/s00220-013-1862-3zbMath1288.82038arXiv1201.2891MaRDI QIDQ393708

Erwin Bolthausen

Publication date: 24 January 2014

Published in: Communications in Mathematical Physics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1201.2891


82C22: Interacting particle systems in time-dependent statistical mechanics


Related Items

Asymptotic mutual information for the balanced binary stochastic block model, Approximate survey propagation for statistical inference, Approximate message passing with spectral initialization for generalized linear models*, Disordered systems insights on computational hardness, Mean-field inference methods for neural networks, Analysis of Bayesian inference algorithms by the dynamical functional approach, Dense limit of the Dawid–Skene model for crowdsourcing and regions of sub-optimality of message passing algorithms, Analysis of random sequential message passing algorithms for approximate inference, Perturbative construction of mean-field equations in extensive-rank matrix factorization and denoising, Optimization of the Sherrington--Kirkpatrick Hamiltonian, Semi-analytic approximate stability selection for correlated data in generalized linear models, A dynamical mean-field theory for learning in restricted Boltzmann machines, A Unifying Tutorial on Approximate Message Passing, Replica analysis of overfitting in generalized linear regression models, The replica symmetric formula for the SK model revisited, TAP approach for multispecies spherical spin glasses II: the free energy of the pure models, Generalized TAP Free Energy, On the concavity of the TAP free energy in the SK model, The free energy of spherical pure \(p\)-spin models: computation from the TAP approach, Large scale stochastic dynamics. Abstracts from the workshop held September 11--17, 2022, Local convexity of the TAP free energy and AMP convergence for \(\mathbb{Z}_2\)-synchronization, High dimensional robust M-estimation: asymptotic variance via approximate message passing, Fluctuation results for multi-species Sherrington-Kirkpatrick model in the replica symmetric regime, On the TAP free energy in the mixed \(p\)-spin models, Notes on computational-to-statistical gaps: predictions using statistical physics, Dynamical approach to the TAP equations for the Sherrington-Kirkpatrick model, Thouless-Anderson-Palmer equations for the Ghatak-Sherrington mean field spin glass model, On convergence of the cavity and Bolthausen's TAP iterations to the local magnetization, Optimization of mean-field spin glasses, Fundamental barriers to high-dimensional regression with convex penalties, Approximate message passing algorithms for rotationally invariant matrices, Computational barriers to estimation from low-degree polynomials, The generalized TAP free energy. II, TAP free energy, spin glasses and variational inference, The overlap gap property and approximate message passing algorithms for \(p\)-spin models, Thouless-Anderson-Palmer equations for generic \(p\)-spin glasses, Universality in polytope phase transitions and message passing algorithms, The TAP-Plefka variational principle for the spherical SK model, Estimation of low-rank matrices via approximate message passing, Algorithmic pure states for the negative spherical perceptron, TAP equations are repulsive, A Morita Type Proof of the Replica-Symmetric Formula for SK, The jamming transition in high dimension: an analytical study of the TAP equations and the effective thermodynamic potential, Statistical mechanics of unsupervised feature learning in a restricted Boltzmann machine with binary synapses



Cites Work