Flow-based Generative Models (FGMs) effectively transform noise into complex data distributions. Incorporating Optimal Transport (OT) to couple noise and data during FGM training has been shown to improve the straightness of flow trajectories, enabling more effective inference. However, existing OT -based methods estimate the OT plan using (mini-)batches of sampled noise and data points, which limits their scalability to large and high-dimensional datasets in FGMs. This paper introduces AlignFlow, a novel approach that leverages Semi-Discrete Optimal Transport (SDOT) to enhance the training of FGMs by establishing an explicit, optimal alignment between noise distribution and data points with guaranteed convergence. SDOT computes a transport map by partitioning the noise space into Laguerre cells, each mapped to a corresponding data point. Experimental results show that Align-Flow improves the performance of a wide range of state-of-the-art FGM algorithms and can be integrated as a plug-and-play component. A generative model in machine learning is designed to produce new data samples that closely resemble those drawn from a given dataset. This task is of fundamental importance and has seen significant advances over the past decades.

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

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.

The task of mapping two or more distributions to a shared representation has many applications including fair representations, batch effect mitigation, and unsupervised domain adaptation. However, most existing formulations only consider the setting of two distributions, and moreover, do not have an identifiable, unique shared latent representation. We use optimal transport theory to consider a natural multiple distribution extension of the Monge assignment problem we call the symmetric Monge map problem and show that it is equivalent to the Wasserstein barycenter problem. Yet, the maps to the barycenter are challenging to estimate. Prior methods often ignore transportation cost, rely on adversarial methods, or only work for discrete distributions. Therefore, our goal is to estimate invertible maps between two or more distributions and their corresponding barycenter via a simple iterative flow method. Our method decouples each iteration into two subproblems: 1) estimate simple distributions and 2) estimate the invertible maps to the barycenter via known closed-form OT results. Our empirical results give evidence that this iterative algorithm approximates the maps to the barycenter.

Given unpaired data from multiple domains, a key challenge is to efficiently exploit these data sources for modeling a target domain. Variants of this problem have been studied in many contexts, such as cross-domain translation and domain adaptation. We propose AlignFlow, a generative modeling framework for learning from multiple domains via normalizing flows. The use of normalizing flows in AlignFlow allows for a) flexibility in specifying learning objectives via adversarial training, maximum likelihood estimation, or a hybrid of the two methods; and b) exact inference of the shared latent factors across domains at test time. We derive theoretical results for the conditions under which AlignFlow guarantees marginal consistency for the different learning objectives. Furthermore, we show that AlignFlow guarantees exact cycle consistency in mapping datapoints from one domain to another. Empirically, AlignFlow can be used for data-efficient density estimation given multiple data sources and shows significant improvements over relevant baselines on unsupervised domain adaptation.