BROJA-2PID: A robust estimator for bivariate partial information decomposition

TL;DR

This paper introduces a robust software implementation for the BROJA-2PID measure of bivariate partial information decomposition, based on cone programming, with proven theoretical properties ensuring reliability.

Contribution

We developed a production-quality software for BROJA-2PID using cone programming, and proved strong duality and equivalence to the original convex formulation.

Findings

Proved strong duality for the cone program

Established equivalence between cone program and convex problem

Provided detailed software implementation and usage instructions

Abstract

Makkeh, Theis, and Vicente found in [8] that Cone Programming model is the most robust to compute the Bertschinger et al. partial information decompostion (BROJA PID) measure [1]. We developed a production-quality robust software that computes the BROJA PID measure based on the Cone Programming model. In this paper, we prove the important property of strong duality for the Cone Program and prove an equivalence between the Cone Program and the original Convex problem. Then describe in detail our software and how to use it.\newline\indent