Convergent Dynamics for Solving the TAP Equations of Ising Models with Arbitrary Rotation Invariant Coupling Matrices

01/24/2019
by   Burak Çakmak, et al.
0

We propose an iterative algorithm for solving the Thouless-Anderson-Palmer (TAP) equations of Ising models with arbitrary rotation invariant (random) coupling matrices. In the large-system limit, as the number of iterations tends to infinity we prove by means of the dynamical functional method that the proposed algorithm converges when the so-called de Almeida Thouless (AT) criterion is fulfilled. Moreover, we obtain an analytical expression for the rate of the convergence.

READ FULL TEXT
research
05/04/2020

A Dynamical Mean-Field Theory for Learning in Restricted Boltzmann Machines

We define a message-passing algorithm for computing magnetizations in Re...
research
01/14/2020

Analysis of Bayesian Inference Algorithms by the Dynamical Functional Approach

We analyze the dynamics of an algorithm for approximate inference with l...
research
02/03/2020

Understanding the dynamics of message passing algorithms: a free probability heuristics

We use freeness assumptions of random matrix theory to analyze the dynam...
research
07/19/2023

Comparative analysis of Jacobi and Gauss-Seidel iterative methods

The paper presents a comparative analysis of iterative numerical methods...
research
02/16/2022

Analysis of Random Sequential Message Passing Algorithms for Approximate Inference

We analyze the dynamics of a random sequential message passing algorithm...
research
06/21/2023

Averaging symmetric positive-definite matrices on the space of eigen-decompositions

We study extensions of Fréchet means for random objects in the space Sym...

Please sign up or login with your details

Forgot password? Click here to reset