Generative Conditional Distributions by Neural (Entropic) Optimal Transport

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Nguyen, Bao, Nguyen, Binh, Nguyen, Hieu Trung, Nguyen, Viet Anh
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914823383547904
author Nguyen, Bao
Nguyen, Binh
Nguyen, Hieu Trung
Nguyen, Viet Anh
author_facet Nguyen, Bao
Nguyen, Binh
Nguyen, Hieu Trung
Nguyen, Viet Anh
contents Learning conditional distributions is challenging because the desired outcome is not a single distribution but multiple distributions that correspond to multiple instances of the covariates. We introduce a novel neural entropic optimal transport method designed to effectively learn generative models of conditional distributions, particularly in scenarios characterized by limited sample sizes. Our method relies on the minimax training of two neural networks: a generative network parametrizing the inverse cumulative distribution functions of the conditional distributions and another network parametrizing the conditional Kantorovich potential. To prevent overfitting, we regularize the objective function by penalizing the Lipschitz constant of the network output. Our experiments on real-world datasets show the effectiveness of our algorithm compared to state-of-the-art conditional distribution learning techniques. Our implementation can be found at https://github.com/nguyenngocbaocmt02/GENTLE.
format Preprint
id arxiv_https___arxiv_org_abs_2406_02317
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Generative Conditional Distributions by Neural (Entropic) Optimal Transport
Nguyen, Bao
Nguyen, Binh
Nguyen, Hieu Trung
Nguyen, Viet Anh
Machine Learning
Artificial Intelligence
Learning conditional distributions is challenging because the desired outcome is not a single distribution but multiple distributions that correspond to multiple instances of the covariates. We introduce a novel neural entropic optimal transport method designed to effectively learn generative models of conditional distributions, particularly in scenarios characterized by limited sample sizes. Our method relies on the minimax training of two neural networks: a generative network parametrizing the inverse cumulative distribution functions of the conditional distributions and another network parametrizing the conditional Kantorovich potential. To prevent overfitting, we regularize the objective function by penalizing the Lipschitz constant of the network output. Our experiments on real-world datasets show the effectiveness of our algorithm compared to state-of-the-art conditional distribution learning techniques. Our implementation can be found at https://github.com/nguyenngocbaocmt02/GENTLE.
title Generative Conditional Distributions by Neural (Entropic) Optimal Transport
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2406.02317