Exponential control of overlap in the replica method for p-spin Sherrington-Kirkpatrick model
Dmitry Panchenko

TL;DR
This paper extends Talagrand's large deviations results for the SK model's partition function moments to all real exponents, providing a new proof with exponential overlap control for the pure p-spin case.
Contribution
It offers a new proof for the large deviations limit in the pure p-spin SK model, enhancing the understanding of overlap control for all real moments.
Findings
Extended Talagrand's limit to all real a ≥ 0
Provided a new proof with exponential overlap control for a ≥ 1
Strengthened the theoretical understanding of the p-spin SK model
Abstract
Recently, Michel Talagrand computed the large deviations limit for the moments of the partition function in the Sherrington-Kirkpatrick model for all real For the limit is given by Guerra's inverse bound and this result extends the classical physicist's replica method that corresponds to integer We give a new proof for in the case of the pure -spin SK model that provides a strong exponential control of the overlap.
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.
