Existence and Uniqueness of Permutation-Invariant Optimizers for Parisi Formula
Victor Issa

TL;DR
This paper establishes the existence and uniqueness of permutation-invariant optimizers for the Parisi formula in mean-field spin glass models, extending previous constrained results to unconstrained systems and deriving bounds for nonconvex models.
Contribution
It introduces a correction term to express the free energy as an optimization over permutation-invariant order parameters without constraints, proving uniqueness in some models.
Findings
Unique optimizer exists for certain permutation-invariant models.
Upper bounds for nonconvex models' free energy are derived.
Results transfer to uncorrected free energy in Ising spin cases.
Abstract
It has recently been shown in [arXiv:2310.06745] that, upon constraining the system to stay in a balanced state, the Parisi formula for the mean-field Potts model can be written as an optimization problem over permutation-invariant functional order parameters. In this paper, we focus on permutation-invariant mean-field spin glass models. After introducing a correction term in the definition of the free energy and without constraining the system, we show that the limit free energy can be written as an optimization problem over permutation-invariant functional order parameters. We also show that for some models this optimization problem admits a unique optimizer. In the case of Ising spins, the correction term can be easily removed, and those results transfer to the uncorrected limit free energy. We also derive an upper bound for the limit free energy of some nonconvex…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsTheoretical and Computational Physics · Quantum many-body systems · Markov Chains and Monte Carlo Methods
