Canonical Divergence Analysis

TL;DR

This paper introduces Canonical Divergence Analysis (CDA), a novel method for analyzing relationships between two potentially unrelated random vectors with different attributes, applicable in diverse fields like biology and architecture.

Contribution

The paper proposes CDA, a new approach that handles vectors with different attributes and distributions, extending beyond existing methods' assumptions.

Findings

CDA effectively analyzes relationships between diverse vectors.

Empirical results demonstrate the method's practical potential.

CDA outperforms traditional techniques in complex scenarios.

Abstract

We aim to analyze the relation between two random vectors that may potentially have both different number of attributes as well as realizations, and which may even not have a joint distribution. This problem arises in many practical domains, including biology and architecture. Existing techniques assume the vectors to have the same domain or to be jointly distributed, and hence are not applicable. To address this, we propose Canonical Divergence Analysis (CDA). We introduce three instantiations, each of which permits practical implementation. Extensive empirical evaluation shows the potential of our method.