Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yao, Rentian, Nitanda, Atsushi, Chen, Xiaohui, Yang, Yun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2502.17738
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909509506564096
author Yao, Rentian
Nitanda, Atsushi
Chen, Xiaohui
Yang, Yun
author_facet Yao, Rentian
Nitanda, Atsushi
Chen, Xiaohui
Yang, Yun
contents Motivated by learning dynamical structures from static snapshot data, this paper presents a distribution-on-scalar regression approach for estimating the density evolution of a stochastic process from its noisy temporal point clouds. We propose an entropy-regularized nonparametric maximum likelihood estimator (E-NPMLE), which leverages the entropic optimal transport as a smoothing regularizer for the density flow. We show that the E-NPMLE has almost dimension-free statistical rates of convergence to the ground truth distributions, which exhibit a striking phase transition phenomenon in terms of the number of snapshots and per-snapshot sample size. To efficiently compute the E-NPMLE, we design a novel particle-based and grid-free coordinate KL divergence gradient descent (CKLGD) algorithm and prove its polynomial iteration complexity. Moreover, we provide numerical evidence on synthetic data to support our theoretical findings. This work contributes to the theoretical understanding and practical computation of estimating density evolution from noisy observations in arbitrary dimensions.
format Preprint
id arxiv_https___arxiv_org_abs_2502_17738
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Learning Density Evolution from Snapshot Data
Yao, Rentian
Nitanda, Atsushi
Chen, Xiaohui
Yang, Yun
Statistics Theory
Computation
Motivated by learning dynamical structures from static snapshot data, this paper presents a distribution-on-scalar regression approach for estimating the density evolution of a stochastic process from its noisy temporal point clouds. We propose an entropy-regularized nonparametric maximum likelihood estimator (E-NPMLE), which leverages the entropic optimal transport as a smoothing regularizer for the density flow. We show that the E-NPMLE has almost dimension-free statistical rates of convergence to the ground truth distributions, which exhibit a striking phase transition phenomenon in terms of the number of snapshots and per-snapshot sample size. To efficiently compute the E-NPMLE, we design a novel particle-based and grid-free coordinate KL divergence gradient descent (CKLGD) algorithm and prove its polynomial iteration complexity. Moreover, we provide numerical evidence on synthetic data to support our theoretical findings. This work contributes to the theoretical understanding and practical computation of estimating density evolution from noisy observations in arbitrary dimensions.
title Learning Density Evolution from Snapshot Data
topic Statistics Theory
Computation
url https://arxiv.org/abs/2502.17738