Minimum-Entropy Coupling Approximation Guarantees Beyond the Majorization Barrier

arXiv2302.11838MaRDI QIDQ6427366

Author name not available (Why is that?)

Publication date: 23 February 2023

Abstract: Given a set of discrete probability distributions, the minimum entropy coupling is the minimum entropy joint distribution that has the input distributions as its marginals. This has immediate relevance to tasks such as entropic causal inference for causal graph discovery and bounding mutual information between variables that we observe separately. Since finding the minimum entropy coupling is NP-Hard, various works have studied approximation algorithms. The work of [Compton, ISIT 2022] shows that the greedy coupling algorithm of [Kocaoglu et al., AAAI 2017] is always within $lo{g}_2(e)approx1.44$ bits of the optimal coupling. Moreover, they show that it is impossible to obtain a better approximation guarantee using the majorization lower-bound that all prior works have used: thus establishing a majorization barrier. In this work, we break the majorization barrier by designing a stronger lower-bound that we call the profile method. Using this profile method, we are able to show that the greedy algorithm is always within $lo{g}_2(e)/eapprox0.53$ bits of optimal for coupling two distributions (previous best-known bound is within 1 bit), and within $(1+lo{g}_2(e))/2approx1.22$ bits for coupling any number of distributions (previous best-known bound is within 1.44 bits). We also examine a generalization of the minimum entropy coupling problem: Concave Minimum-Cost Couplings. We are able to obtain similar guarantees for this generalization in terms of the concave cost function. Additionally, we make progress on the open problem of [Kovav{c}evi'c et al., Inf. Comput. 2015] regarding NP membership of the minimum entropy coupling problem by showing that any hardness of minimum entropy coupling beyond NP comes from the difficulty of computing arithmetic in the complexity class NP. Finally, we present exponential-time algorithms for computing the exactly optimal solution.

This page was built for publication: Minimum-Entropy Coupling Approximation Guarantees Beyond the Majorization Barrier

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6427366)