Optimization of random high-dimensional functions: Structure and algorithms
From MaRDI portal
Abstract: Replica symmetry breaking postulates that near optima of spin glass Hamiltonians have an ultrametric structure. Namely, near optima can be associated to leaves of a tree, and the Euclidean distance between them corresponds to the distance along this tree. We survey recent progress towards a rigorous proof of this picture in the context of mixed -spin spin glass models. We focus in particular on the following topics: ~The structure of critical points of the Hamiltonian; ~The realization of the ultrametric tree as near optima of a suitable TAP free energy; ~The construction of efficient optimization algorithm that exploits this picture.
This page was built for publication: Optimization of random high-dimensional functions: Structure and algorithms
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6402692)
