Infinite-dimensional Hamilton-Jacobi equations for statistical inference on sparse graphs
From MaRDI portal
Publication:6410239
Authors: Tomas Dominguez, J-C. Mourrat 
Publication date: 9 September 2022
Abstract: We study the well-posedness of an infinite-dimensional Hamilton-Jacobi equation posed on the set of non-negative measures and with a monotonic non-linearity. Our results will be used in a companion work to propose a conjecture and prove partial results concerning the asymptotic mutual information in the assortative stochastic block model in the sparse regime. The equation we consider is naturally stated in terms of the Gateaux derivative of the solution, unlike previous works in which the derivative is usually of transport type. We introduce an approximating family of finite-dimensional Hamilton-Jacobi equations, and use the monotonicity of the non-linearity to show that no boundary condition needs to be prescribed to establish well-posedness. The solution to the infinite-dimensional Hamilton-Jacobi equation is then defined as the limit of these approximating solutions. In the special setting of a convex non-linearity, we also provide a Hopf-Lax variational representation of the solution.
This page was built for publication: Infinite-dimensional Hamilton-Jacobi equations for statistical inference on sparse graphs
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6410239)
