Convergence of linear programming hierarchies for Gibbs states of spin systems

Authors: Hamza Fawzi, Omar Fawzi

TMLR 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical In this paper we study certified algorithms to approximate µ(f) when f is a local function, i.e., depending only on variables in a set B V of small size. ... We study two hierarchies of linear programs giving upper and lower bounds on µ(f). ... The main result in this section shows that if µ has spatial mixing, then the linear programming-based upper and lower bounds will converge exponentially fast (in dist(supp(f), Λc)) to µ(f). ... We are now ready to state our main convergence theorem.
Researcher Affiliation Academia Hamza Fawzi1 and Omar Fawzi2 1DAMTP, University of Cambridge, United Kingdom 2Inria, ENS de Lyon, UCBL, LIP, France
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks. It describes mathematical methods and theorems.
Open Source Code No The paper does not provide any statements about releasing code or links to source code repositories for the described methodology.
Open Datasets No The paper is theoretical and focuses on 'Gibbs states of spin systems' and 'Ising models on a d-dimensional grid' which are mathematical models, not specific datasets used for empirical evaluation. Thus, it does not provide access information for open datasets.
Dataset Splits No This paper is theoretical and does not describe experiments with datasets, therefore it does not specify dataset splits.
Hardware Specification No The paper is theoretical and does not describe experimental implementation, hence no specific hardware details are provided.
Software Dependencies No The paper is theoretical and does not describe experimental implementation, hence no specific software dependencies or version numbers are provided.
Experiment Setup No This paper is theoretical and focuses on mathematical proofs and convergence rates, not on empirical experimentation. Therefore, it does not contain specific experimental setup details or hyperparameters.