Number 12 of 12 · November 22, 2026

Invertible Transport Between Sample-Only Distributions via Projected Characteristic Functions

In the authors' words: "Many useful latent distributions can be sampled but do not have a tractable density." SI MIND's plain-English page for this paper is pending.

Summary pending

SI MIND writes its plain-English page from the abstract and the paper's details only, and it has not written this one yet. The abstract below is the authors' own summary, quoted as published on arXiv.

The abstract, by the authors

Many useful latent distributions can be sampled but do not have a tractable density. Such distributions may be represented by empirical collections of real-world observations or generated by scientific simulators and black-box generative models. These sample-only priors cannot be used directly in likelihood-based normalizing flows, which require evaluating the prior density. We propose Projected Characteristic-Function matching (PCF), a density-free framework for learning an invertible map between a data distribution and a prior specified only through samples. Our method aligns distributions using projected empirical characteristic functions, eliminating the need for density estimation, adversarial training, or paired observations. To address the non-uniqueness of the transport map, we introduce an optional transport regularizer that selects lower-displacement transformations while preserving endpoint alignment. We benchmark PCF on controlled transports, sample-efficiency studies, and high-dimensional alignment tasks. PCF matches the accuracy of kernel MMD on the controlled benchmark and on raw-pixel MNIST-USPS at a cost linear in the batch size, and it is more sample-efficient, achieving lower endpoint error than MMD in 13 of 15 paired runs across library sizes. By avoiding pairwise kernel evaluation, it reduces discrepancy memory by 29.8% and trains at batch sizes where kernel MMD exceeds GPU memory. These results show that PCF provides accurate and efficient invertible transport, particularly in sample- and memory-limited settings.

Quoted from arXiv:2611.26187. The research and its words belong to its authors.

The authors

Juan Gutiérrez, Victor Gutiérrez-García, José Luis Blanco-Murillo

Credit for this research belongs to its authors. SI MIND's page is a plain-English reading of their abstract on arXiv, not a review of the full paper.