Spin-glass phase diagnostics on VAE latents allow tuning to edge-of-stability for improved generation and OOD detection.
A Dynamic Programming Approach to the Parisi Functional
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
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].
fields
cond-mat.dis-nn 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
High-Dimensional Latents Should Be Diagnosed Through Phase Structure
Spin-glass phase diagnostics on VAE latents allow tuning to edge-of-stability for improved generation and OOD detection.