Cooperative Distribution Alignment via JSD Upper Bound

TL;DR

This paper introduces a unified, non-adversarial framework for distribution alignment based on minimizing an upper bound on Jensen-Shannon Divergence, simplifying optimization and enabling effective alignment of multiple distributions.

Contribution

It unifies and generalizes flow-based distribution alignment methods under a cooperative, non-adversarial framework linked to JSD upper bound minimization.

Findings

Empirical results show improved alignment on simulated datasets.

Demonstrates effectiveness on real-world datasets.

Provides a natural evaluation metric for distribution alignment.

Abstract

Unsupervised distribution alignment estimates a transformation that maps two or more source distributions to a shared aligned distribution given only samples from each distribution. This task has many applications including generative modeling, unsupervised domain adaptation, and socially aware learning. Most prior works use adversarial learning (i.e., min-max optimization), which can be challenging to optimize and evaluate. A few recent works explore non-adversarial flow-based (i.e., invertible) approaches, but they lack a unified perspective and are limited in efficiently aligning multiple distributions. Therefore, we propose to unify and generalize previous flow-based approaches under a single non-adversarial framework, which we prove is equivalent to minimizing an upper bound on the Jensen-Shannon Divergence (JSD). Importantly, our problem reduces to a min-min, i.e., cooperative, problem and can provide a natural evaluation metric for unsupervised distribution alignment. We show empirical results on both simulated and real-world datasets to demonstrate the benefits of our approach. Code is available at https://github.com/inouye-lab/alignment-upper-bound.