TAP free energy, spin glasses and variational inference

DOI10.1214/20-AOP1443zbMath1467.60025arXiv1808.07890OpenAlexW3125529942MaRDI QIDQ2227708

Yanyan Li

Publication date: 15 February 2021

Published in: The Annals of Probability (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1808.07890

zbMATH Keywords

Sherrington-Kirkpatrick modelBayesian inferencefree probabilityKac-Rice formulaTAP complexity

Mathematics Subject Classification ID

Bayesian inference (62F15) Large deviations (60F10)

Related Items (6)

On the concavity of the TAP free energy in the SK model ⋮ The TAP free energy for high-dimensional linear regression ⋮ Landscape complexity beyond invariance and the elastic manifold ⋮ Local convexity of the TAP free energy and AMP convergence for \(\mathbb{Z}_2\)-synchronization ⋮ Exponential growth of random determinants beyond invariance ⋮ Triviality of the geometry of mixed \(p\)-spin spherical Hamiltonians with external field

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• An iterative construction of solutions of the TAP equations for the Sherrington-Kirkpatrick model
• Free convolution with a semicircular distribution and eigenvalues of spiked deformations of Wigner matrices
• Orientability and diffusion maps
• Angular synchronization by eigenvectors and semidefinite programming
• Correlation clustering
• Spin glasses and Stein's method
• Large deviations techniques and applications.
• The eigenvalues of random symmetric matrices
• Limit laws for random matrices and free products
• An introduction to MCMC for machine learning
• On the TAP free energy in the mixed \(p\)-spin models
• The complexity of spherical \(p\)-spin models: a second moment approach
• Fundamental limits of symmetric low-rank matrix estimation
• Optimality and sub-optimality of PCA. I: Spiked random matrix models
• Broken replica symmetry bounds in the mean field spin glass model
• The zero set of a real analytic function
• The adaptive interpolation method: a simple scheme to prove replica formulas in Bayesian inference
• Thouless-Anderson-Palmer equations for generic \(p\)-spin glasses
• Complexity of random smooth functions on the high-dimensional sphere
• Measurable selections of extrema
• Phase transition of the largest eigenvalue for nonnull complex sample covariance matrices
• Complexity of Random Energy Landscapes, Glass Transition, and Absolute Value of the Spectral Determinant of Random Matrices
• Phase transitions in semidefinite relaxations
• Graphical Models, Exponential Families, and Variational Inference
• Information, Physics, and Computation
• The Markov chain Monte Carlo revolution
• An Introduction to Random Matrices
• Mean-field equations for spin models with orthogonal interaction matrices
• On the free convolution with a semi-circular distribution
• On the formal equivalence of the TAP and thermodynamic methods in the SK model
• Asymptotic mutual information for the balanced binary stochastic block model
• Statistical Physics of Spin Glasses and Information Processing
• Random Matrices and Complexity of Spin Glasses
• The Landscape of the Spiked Tensor Model
• The Dynamics of Message Passing on Dense Graphs, with Applications to Compressed Sensing
• Random Fields and Geometry
• Semidefinite programs on sparse random graphs and their application to community detection
• A Simple Approach to the Global Regime of Gaussian Ensembles of Random Matrices
• Mean Field Models for Spin Glasses

This page was built for publication: TAP free energy, spin glasses and variational inference