stat.MLNov 16, 2026
SaveComments on "Deep Fréchet Regression"
Organizations: Department of Biostatistics & Bioinformatics, Duke University · Department of Biostatistics & Bioinformatics and Department of Computer Science, Duke University
Abstract
We discuss the Journal of the American Statistical Association (JASA) discussion paper "Deep Fréchet Regression" and explore an alternative perspective based on conditional flow matching. We propose learning covariate-dependent transport directly within the response space, avoiding separate manifold learning and reverse mapping. This perspective offers a potentially more flexible framework for incorporating geometric structure and modeling full conditional distributions.
Figures & tables
Figure 1: Illustration of a covariate-dependent flow on a non-Euclidean response space, transporting a reference distribution toward the conditional distribution of the observed response.