Saved in:
Bibliographic Details
Main Authors: Kim, Kyum, Chen, Yaqing, Dubey, Paromita
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.17072
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914103563386880
author Kim, Kyum
Chen, Yaqing
Dubey, Paromita
author_facet Kim, Kyum
Chen, Yaqing
Dubey, Paromita
contents Regression with non-Euclidean responses -- e.g., probability distributions, networks, symmetric positive-definite matrices, and compositions -- has become increasingly important in modern applications. In this paper, we propose deep Fréchet neural networks (DFNNs), an end-to-end deep learning framework for predicting non-Euclidean responses -- which are considered as random objects in a metric space -- from Euclidean predictors. Our method leverages the representation-learning power of deep neural networks (DNNs) to the task of approximating conditional Fréchet means of the response given the predictors, the metric-space analogue of conditional expectations, by minimizing a Fréchet risk. The framework is highly flexible, accommodating diverse metrics and high-dimensional predictors. We establish a universal approximation theorem for DFNNs, advancing the state-of-the-art of neural network approximation theory to general metric-space-valued responses without making model assumptions or relying on local smoothing. Empirical studies on synthetic distributional and network-valued responses, as well as a real-world application to predicting employment occupational compositions, demonstrate that DFNNs consistently outperform existing methods.
format Preprint
id arxiv_https___arxiv_org_abs_2510_17072
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DFNN: A Deep Fréchet Neural Network Framework for Learning Metric-Space-Valued Responses
Kim, Kyum
Chen, Yaqing
Dubey, Paromita
Machine Learning
Methodology
Regression with non-Euclidean responses -- e.g., probability distributions, networks, symmetric positive-definite matrices, and compositions -- has become increasingly important in modern applications. In this paper, we propose deep Fréchet neural networks (DFNNs), an end-to-end deep learning framework for predicting non-Euclidean responses -- which are considered as random objects in a metric space -- from Euclidean predictors. Our method leverages the representation-learning power of deep neural networks (DNNs) to the task of approximating conditional Fréchet means of the response given the predictors, the metric-space analogue of conditional expectations, by minimizing a Fréchet risk. The framework is highly flexible, accommodating diverse metrics and high-dimensional predictors. We establish a universal approximation theorem for DFNNs, advancing the state-of-the-art of neural network approximation theory to general metric-space-valued responses without making model assumptions or relying on local smoothing. Empirical studies on synthetic distributional and network-valued responses, as well as a real-world application to predicting employment occupational compositions, demonstrate that DFNNs consistently outperform existing methods.
title DFNN: A Deep Fréchet Neural Network Framework for Learning Metric-Space-Valued Responses
topic Machine Learning
Methodology
url https://arxiv.org/abs/2510.17072