Guardado en:
Detalles Bibliográficos
Autores principales: Fujikawa, Mitsuhiro, Akimoto, Yohei, Sakuma, Jun, Fukuchi, Kazuto
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2405.16906
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916518691864576
author Fujikawa, Mitsuhiro
Akimoto, Yohei
Sakuma, Jun
Fukuchi, Kazuto
author_facet Fujikawa, Mitsuhiro
Akimoto, Yohei
Sakuma, Jun
Fukuchi, Kazuto
contents Transfer learning enhances prediction accuracy on a target distribution by leveraging data from a source distribution, demonstrating significant benefits in various applications. This paper introduces a novel dissimilarity measure that utilizes vicinity information, i.e., the local structure of data points, to analyze the excess error in classification under covariate shift, a transfer learning setting where marginal feature distributions differ but conditional label distributions remain the same. We characterize the excess error using the proposed measure and demonstrate faster or competitive convergence rates compared to previous techniques. Notably, our approach is effective in the support non-containment assumption, which often appears in real-world applications, holds. Our theoretical analysis bridges the gap between current theoretical findings and empirical observations in transfer learning, particularly in scenarios with significant differences between source and target distributions.
format Preprint
id arxiv_https___arxiv_org_abs_2405_16906
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift
Fujikawa, Mitsuhiro
Akimoto, Yohei
Sakuma, Jun
Fukuchi, Kazuto
Machine Learning
Transfer learning enhances prediction accuracy on a target distribution by leveraging data from a source distribution, demonstrating significant benefits in various applications. This paper introduces a novel dissimilarity measure that utilizes vicinity information, i.e., the local structure of data points, to analyze the excess error in classification under covariate shift, a transfer learning setting where marginal feature distributions differ but conditional label distributions remain the same. We characterize the excess error using the proposed measure and demonstrate faster or competitive convergence rates compared to previous techniques. Notably, our approach is effective in the support non-containment assumption, which often appears in real-world applications, holds. Our theoretical analysis bridges the gap between current theoretical findings and empirical observations in transfer learning, particularly in scenarios with significant differences between source and target distributions.
title Harnessing the Power of Vicinity-Informed Analysis for Classification under Covariate Shift
topic Machine Learning
url https://arxiv.org/abs/2405.16906