Generative Modeling from Black-Box Corruptions via Self-Consistent Stochastic Interpolants

ICLR 2026 Conference Submission13106 Authors

Keywords: generative models, corrupted data, inverse problems, stochastic interpolants

TL;DR: We develop a novel transport-based approach to learn a generative model of a data distribution using only access to corrupted observations from a black-box observation map

Abstract: Transport-based methods have emerged as a leading paradigm for building generative models from large, clean datasets. However, in many scientific and engineering domains, clean data are often unavailable: instead, we only observe measurements corrupted through a noisy, ill-conditioned channel. A generative model for the original data thus requires solving an inverse problem at the level of distributions. In this work, we introduce a novel approach to this task based on Stochastic Interpolants: we iteratively update a transport map between corrupted and clean data samples using only access to the corrupted dataset as well as black box access to the corruption channel. Under appropriate conditions, this iterative procedure converges towards a self-consistent transport map that effectively inverts the corruption channel, thus enabling a generative model for the clean data. The resulting method (i) is computationally efficient compared to variational alternatives, (ii) highly flexible, handling arbitrary nonlinear forward models with only black-box access, and (iii) enjoys theoretical guarantees. We demonstrate superior performance on inverse problems in natural image processing and scientific reconstruction, and establish convergence guarantees of the scheme under appropriate assumptions.

Primary Area: generative models

Submission Number: 13106