A Dynamic Programming Approach to the Parisi Functional

Abstract

G.Parisi predicted an important variational formula for the thermodynamic limit of the intensive free energy for a class of mean field spin glasses. In this paper, we present an elementary approach to the study of the Parisi functional using stochastic dynamic programing and semi-linear PDE. We give a derivation of important properties of the Parisi PDE avoiding the use of Ruelle Probability Cascades and Cole-Hopf transformations. As an application, we give a simple proof of the strict convexity of the Parisi functional, which was recently proved by Auffinger and Chen in [2].

Edits to take in to account referee's comments and suggestions. To appear in Proceedings of the AMS

Cited by in corpus (26)

• Extremal Cuts of Sparse Random Graphs
• Suboptimality of local algorithms for a class of max-cut problems
• Spectral gap estimates in mean field spin glasses
• Some Properties of the Phase Diagram for Mixed $p$-Spin Glasses
• Free energy in multi-species mixed $p$-spin spherical models
• On the energy landscape of the mixed even $p$-spin model
• On the TAP free energy in the mixed $p$-spin models
• The generalized TAP free energy II
• Algorithmic Thresholds in Mean Field Spin Glasses
• Localization of directed polymers with general reference walk
• Optimizing Mean Field Spin Glasses with External Field
• The Legendre structure of the Parisi formula
• The Overlap Gap Property in Principal Submatrix Recovery
• Phase transition in random tensors with multiple independent spikes
• On spin distributions for generic p-spin models
• Optimization on Sparse Random Hypergraphs and Spin Glasses
• Variational representations for the Parisi functional and the two-dimensional Guerra-Talagrand bound
• The SK model is infinite step replica symmetry breaking at zero temperature
• Phase transition in the spiked random tensor with Rademacher prior
• Parisi formula for the ground state energy in the mixed p-spin model
• On the unbalanced cut problem and the generalized Sherrington-Kirkpatrick model
• The ${\ell }^p$-Gaussian-Grothendieck problem with vector spins
• Fluctuations of the free energy in the mixed $p$-spin models with external field
• Tight Lipschitz Hardness for Optimizing Mean Field Spin Glasses
• On ${\ell }_p$-Gaussian-Grothendieck problem
• Free Energy Subadditivity for Symmetric Random Hamiltonians