We build a new class of generative algorithms capable of efficiently learning an arbitrary target distribution from possibly scarce, high-dimensional data and subsequently generate new samples. These generative algorithms are particle-based and are constructed as gradient flows of Lipschitz-regularized Kullback-Leibler or other f-divergences, where data from a source distribution can be stably transported as particles, towards the vicinity of the target distribution. As a highlighted result in data integration, we demonstrate that the proposed algorithms correctly transport gene expression data points with dimension exceeding 54K, while the sample size is typically only in the hundreds.
@article{arxiv.2210.17230,
title = {Lipschitz-regularized gradient flows and generative particle algorithms for high-dimensional scarce data},
author = {Hyemin Gu and Panagiota Birmpa and Yannis Pantazis and Luc Rey-Bellet and Markos A. Katsoulakis},
journal= {arXiv preprint arXiv:2210.17230},
year = {2024}
}