Hamilton-Jacobi equations for mean-field disordered systems
read the original abstract
We argue that Hamilton-Jacobi equations provide a convenient and intuitive approach for studying the large-scale behavior of mean-field disordered systems. This point of view is illustrated on the problem of inference of a rank-one matrix. We compute the large-scale limit of the free energy by showing that it satisfies an approximate Hamilton-Jacobi equation with asymptotically vanishing viscosity parameter and error term.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Parisi's formula is a Hamilton-Jacobi equation in Wasserstein space
Parisi's formula is recast as the solution of a Hamilton-Jacobi equation in the Wasserstein space of probability measures on the positive half-line.
-
Concentration of the matrix-valued minimum mean-square error in optimal Bayesian inference
The matrix-valued MMSE concentrates in the large-system limit for optimal Bayesian inference of vector-valued signals.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.