Litcius/Paper detail

Sampling from the Sherrington-Kirkpatrick Gibbs measure via algorithmic stochastic localization

A. El Alaoui, Andrea Montanari, Mark Sellke

20222022 IEEE 63rd Annual Symposium on Foundations of Computer Science (FOCS)29 citationsDOI

Abstract

We consider the Sherrington-Kirkpatrick model of spin glasses at high-temperature and no external field, and study the problem of sampling from the Gibbs distribution $\mu$ in polynomial time. We prove that, for any inverse temperature $\beta\lt 1/2$, there exists an algorithm with complexity $O(n^{2})$ that samples from a distribution $\mu^{\text{als}}$ which is close in normalized Wasserstein distance to $\mu$. Namely, there exists a coupling of $\mu$ and $\mu^{\text{alg}}$ such that if $(x,x^{\text{als}})\in\{-1,+1\}^{n}\times\{-1,+1\}^{n}$ is a pair drawn from this coupling, then $n^{-1}\mathbb{E}\{\|x-x^{\text{ald}}\|_{2}^{2}\}=o_{n}(1)$. The best previous results, by Bauerschmidt and Bodineau [BB19] and by Eldan, Koehler, Zeitouni [EKZ21], implied efficient algorithms to approximately sample (under a stronger metric) for $\beta\lt 1/4$. We complement this result with a negative one, by introducing a suitable “stability” property for sampling algorithms, which is verified by many standard techniques. We prove that no stable algorithm can approximately sample for $\beta$>1, even under the normalized Wasserstein metric. Our sampling method is based on an algorithmic implementation of stochastic localization, which progressively tilts the measure $\mu$ towards a single configuration, together with an approximate message passing algorithm that is used to approximate the mean of the tilted measure.

Topics & Concepts

Measure (data warehouse)Complement (music)CombinatoricsMathematicsInverseGibbs samplingMetric (unit)Coupling (piping)Discrete mathematicsSampling (signal processing)Distribution (mathematics)Spin glassGibbs measurePhysicsComputer scienceMathematical analysisStatisticsQuantum mechanicsGeometryBayesian probabilityGeneOperations managementPhenotypeMechanical engineeringDatabaseChemistryOpticsBiochemistryEngineeringDetectorEconomicsComplementationMarkov Chains and Monte Carlo MethodsTopological and Geometric Data AnalysisTheoretical and Computational Physics