ICML 2026poster0 citations
Adapting Noise to Data: Generative Flows from Learned 1D Processes
Jannis Chemseddine, Gregor Kornhardt, Richard Duong, Gabriele Steidl
Abstract
The default Gaussian latent in flow-based generative models poses challenges when learning certain distributions such as heavy-tailed ones. We introduce a general framework for learning data-adaptive latent distributions using one-dimensional quantile functions, optimized via the Wasserstein distance between noise and data. The quantile-based parameterization naturally adapts to both heavy-tailed and compactly supported distributions and shortens transport paths. Numerical results confirm the method’s flexibility and effectiveness achieved with negligible computational overhead.
BibTeX
@inproceedings{
chemseddine2026adapting,
title={Adapting Noise to Data: Generative Flows from Learned 1D Processes},
author={Jannis Chemseddine and Gregor Kornhardt and Richard Duong and Gabriele Steidl},
booktitle={Forty-third International Conference on Machine Learning},
year={2026},
url={https://openreview.net/forum?id=vLQO6nrpYq}
}