Quantitative Correlation Inequalities via Semigroup Interpolation

TL;DR

This paper develops a new semigroup interpolation method to transform qualitative correlation inequalities into quantitative bounds, providing near-optimal estimates for Gaussian and FKG inequalities across various settings.

Contribution

It introduces a novel approach combining extremal power series results and harmonic analysis to derive quantitative correlation inequalities, including for Gaussian and FKG cases.

Findings

Quantitative bounds for Gaussian correlation inequality using Hermite coefficients.

Extended FKG inequality with explicit correlation bounds for continuous and discrete spaces.

New techniques applicable to a broad class of correlation inequalities.

Abstract

Most correlation inequalities for high-dimensional functions in the literature, such as the Fortuin-Kasteleyn-Ginibre (FKG) inequality and the celebrated Gaussian Correlation Inequality of Royen, are qualitative statements which establish that any two functions of a certain type have non-negative correlation. In this work we give a general approach that can be used to bootstrap many qualitative correlation inequalities for functions over product spaces into quantitative statements. The approach combines a new extremal result about power series, proved using complex analysis, with harmonic analysis of functions over product spaces. We instantiate this general approach in several different concrete settings to obtain a range of new and near-optimal quantitative correlation inequalities, including: $\bullet$ A quantitative version of Royen's celebrated Gaussian Correlation Inequality. Royen (2014) confirmed a conjecture, open for 40 years, stating that any two symmetric, convex sets must be non-negatively correlated under any centered Gaussian distribution. We give a lower bound on the correlation in terms of the vector of degree-2 Hermite coefficients of the two convex sets, analogous to the correlation bound for monotone Boolean functions over $\{0,1\}^n$ obtained by Talagrand (1996). $\bullet$ A quantitative version of the well-known FKG inequality for monotone functions over any finite product probability space, generalizing the quantitative correlation bound for monotone Boolean functions over $\{0,1\}^n$ obtained by Talagrand (1996). The only prior generalization of which we are aware is due to Keller (2008, 2009, 2012), which extended Talagrand's result to product distributions over $\{0,1\}^n$. We also give two different quantitative versions of the FKG inequality for monotone functions over the continuous domain $[0,1]^n$, answering a question of Keller (2009).