Work

Sampling from the Sherrington-Kirkpatrick Model up to Criticality

Year: 2026

Type: preprint

Abstract: We prove that the simulated annealing algorithm efficiently samples from the Sherrington-Kirkpatrick model at inverse temperature $β< 1$ to an arbitrary inverse polynomial accuracy in total variation.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.17717

Authors: Du, Hang, Huang, Brice, Mohanty, Sidhanth, Rajaraman, Amit

Institutions: Stanford University, Northwestern University

Language: English

Topic: Markov Chains and Monte Carlo Methods

Subfield: Statistics and Probability

Field: Mathematics

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, Simons Institute for the Theory of Computing, University of California Berkeley, Division of Mathematical Sciences

Awards: Collaboration on the Theoretical Foundations of Deep Learning, G6763018728

OpenAlex ID: W7221750656

Cites: 16

Cited by: 3

Related to: 10