Free energy of multi-layer generalized linear models
From MaRDI portal
Abstract: We compute the high-dimensional limit of the free energy associated with a multi-layer generalized linear model. Under certain technical assumptions, we identify the limit in terms of a variational formula. The approach is to first show that the limit is a solution to a Hamilton-Jacobi equation whose initial condition is related to the limiting free energy of a model with one fewer layer. Then, we conclude by an iteration.
Recommendations
- Generalised free energy and active inference
- Inference for Generalized Linear Models via Alternating Directions and Bethe Free Energy Minimization
- Properties of Bethe Free Energies and Message Passing in Gaussian Models
- Penalized maximum likelihood estimation of multi-layered Gaussian graphical models
- Matrix inference and estimation in multi-layer models*
- Strict convexity of the free energy for a class of non-convex gradient models
- Free-energy bounds for hierarchical spin models
- The free energy of a class of Hopfield models
- Measuring the complexity of generalized linear hierarchical models
- An alternative view of variational Bayes and asymptotic approximations of free energy
Cites work
- A mechanical approach to mean field spin models
- Concentration inequalities. A nonasymptotic theory of independence
- Convex Analysis
- Entropy and mutual information in models of deep neural networks*
- Extending the Parisi formula along a Hamilton-Jacobi equation
- Hamilton-Jacobi equations for finite-rank matrix inference
- Hamilton-Jacobi equations for mean-field disordered systems
- Hopf Formula and Multitime Hamilton-Jacobi Equations
- scientific article; zbMATH DE number 1751767 (Why is no real title available?)
- scientific article; zbMATH DE number 5681750 (Why is no real title available?)
- Mutual information for low-rank even-order symmetric tensor estimation
- Nonconvex interactions in mean-field spin glasses
- On Hopf's formulas for solutions of Hamilton-Jacobi equations
- Optimal errors and phase transitions in high-dimensional generalized linear models
- Replica symmetry breaking in mean-field spin glasses through the Hamilton-Jacobi technique
- The adaptive interpolation method for proving replica formulas. Applications to the Curie–Weiss and Wigner spike models
- The adaptive interpolation method: a simple scheme to prove replica formulas in Bayesian inference
Cited in
(8)- Mutual information for the sparse stochastic block model
- Infinite-dimensional Hamilton-Jacobi equations for statistical inference on sparse graphs
- Envelope representation of Hamilton–Jacobi equations from spin glasses
- Color symmetry and ferromagnetism in Potts spin glass
- Hamilton-Jacobi equations from mean-field spin glasses
- On free energy of non-convex multi-species spin glasses
- Differentiability and overlap concentration in optimal Bayesian inference
- Fundamental limits of overparametrized shallow neural networks for supervised learning
This page was built for publication: Free energy of multi-layer generalized linear models
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6155616)