Transfer Learning for Functional Mean Estimation: Phase Transition and Adaptive Algorithms

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Cai, T. Tony, Kim, Dongwoo, Pu, Hongming
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911817716989952
author Cai, T. Tony
Kim, Dongwoo
Pu, Hongming
author_facet Cai, T. Tony
Kim, Dongwoo
Pu, Hongming
contents This paper studies transfer learning for estimating the mean of random functions based on discretely sampled data, where, in addition to observations from the target distribution, auxiliary samples from similar but distinct source distributions are available. The paper considers both common and independent designs and establishes the minimax rates of convergence for both designs. The results reveal an interesting phase transition phenomenon under the two designs and demonstrate the benefits of utilizing the source samples in the low sampling frequency regime. For practical applications, this paper proposes novel data-driven adaptive algorithms that attain the optimal rates of convergence within a logarithmic factor simultaneously over a large collection of parameter spaces. The theoretical findings are complemented by a simulation study that further supports the effectiveness of the proposed algorithms
format Preprint
id arxiv_https___arxiv_org_abs_2401_12331
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Transfer Learning for Functional Mean Estimation: Phase Transition and Adaptive Algorithms
Cai, T. Tony
Kim, Dongwoo
Pu, Hongming
Statistics Theory
Primary 62J05, secondary 62G20
This paper studies transfer learning for estimating the mean of random functions based on discretely sampled data, where, in addition to observations from the target distribution, auxiliary samples from similar but distinct source distributions are available. The paper considers both common and independent designs and establishes the minimax rates of convergence for both designs. The results reveal an interesting phase transition phenomenon under the two designs and demonstrate the benefits of utilizing the source samples in the low sampling frequency regime. For practical applications, this paper proposes novel data-driven adaptive algorithms that attain the optimal rates of convergence within a logarithmic factor simultaneously over a large collection of parameter spaces. The theoretical findings are complemented by a simulation study that further supports the effectiveness of the proposed algorithms
title Transfer Learning for Functional Mean Estimation: Phase Transition and Adaptive Algorithms
topic Statistics Theory
Primary 62J05, secondary 62G20
url https://arxiv.org/abs/2401.12331