Work

Comments on "Deep Fréchet Regression"

Year: 2026
Type: preprint
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.
Institution: Duke University
Language: English
Open Access status: green
OpenAlex ID: W7235338520
Cites: 5
Cited by:
Related to: 10