Sinkhorn algorithms for entropic vector quantile regression

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Kato, Kengo, Wang, Boyu
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915882986373120
author Kato, Kengo
Wang, Boyu
author_facet Kato, Kengo
Wang, Boyu
contents Vector quantile regression (VQR) is an optimal transport (OT)-based framework that extends linear quantile regression to vector-valued response variables and can be formulated as an OT problem with a mean-independence constraint. In this paper, we study two Sinkhorn-type algorithms for VQR with entropic regularization, building on our previous work on its duality theory. The first is a direct adaptation of the classical Sinkhorn iteration based on solving the full Schrödinger-type system characterizing the dual potentials, which requires solving an implicit functional equation at each iteration. The second algorithm, which is new in the literature, replaces the implicit update with a projected gradient step, resulting in a modified scheme that is computationally more practical. For both algorithms, and for general compactly supported marginals, we establish linear convergence in both the dual objective value and the iterates. A key innovation in our analysis is the derivation of explicit quantitative bounds on the dual potentials and Sinkhorn iterates.
format Preprint
id arxiv_https___arxiv_org_abs_2603_21554
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Sinkhorn algorithms for entropic vector quantile regression
Kato, Kengo
Wang, Boyu
Optimization and Control
Statistics Theory
49Q22, 62G08, 90C25
Vector quantile regression (VQR) is an optimal transport (OT)-based framework that extends linear quantile regression to vector-valued response variables and can be formulated as an OT problem with a mean-independence constraint. In this paper, we study two Sinkhorn-type algorithms for VQR with entropic regularization, building on our previous work on its duality theory. The first is a direct adaptation of the classical Sinkhorn iteration based on solving the full Schrödinger-type system characterizing the dual potentials, which requires solving an implicit functional equation at each iteration. The second algorithm, which is new in the literature, replaces the implicit update with a projected gradient step, resulting in a modified scheme that is computationally more practical. For both algorithms, and for general compactly supported marginals, we establish linear convergence in both the dual objective value and the iterates. A key innovation in our analysis is the derivation of explicit quantitative bounds on the dual potentials and Sinkhorn iterates.
title Sinkhorn algorithms for entropic vector quantile regression
topic Optimization and Control
Statistics Theory
49Q22, 62G08, 90C25
url https://arxiv.org/abs/2603.21554