Stability-based Generalization Analysis of Randomized Coordinate Descent for Pairwise Learning

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Wu, Liang, Hu, Ruixi, Lei, Yunwen
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909522421874688
author Wu, Liang
Hu, Ruixi
Lei, Yunwen
author_facet Wu, Liang
Hu, Ruixi
Lei, Yunwen
contents Pairwise learning includes various machine learning tasks, with ranking and metric learning serving as the primary representatives. While randomized coordinate descent (RCD) is popular in various learning problems, there is much less theoretical analysis on the generalization behavior of models trained by RCD, especially under the pairwise learning framework. In this paper, we consider the generalization of RCD for pairwise learning. We measure the on-average argument stability for both convex and strongly convex objective functions, based on which we develop generalization bounds in expectation. The early-stopping strategy is adopted to quantify the balance between estimation and optimization. Our analysis further incorporates the low-noise setting into the excess risk bound to achieve the optimistic bound as $O(1/n)$, where $n$ is the sample size.
format Preprint
id arxiv_https___arxiv_org_abs_2503_01530
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Stability-based Generalization Analysis of Randomized Coordinate Descent for Pairwise Learning
Wu, Liang
Hu, Ruixi
Lei, Yunwen
Machine Learning
Pairwise learning includes various machine learning tasks, with ranking and metric learning serving as the primary representatives. While randomized coordinate descent (RCD) is popular in various learning problems, there is much less theoretical analysis on the generalization behavior of models trained by RCD, especially under the pairwise learning framework. In this paper, we consider the generalization of RCD for pairwise learning. We measure the on-average argument stability for both convex and strongly convex objective functions, based on which we develop generalization bounds in expectation. The early-stopping strategy is adopted to quantify the balance between estimation and optimization. Our analysis further incorporates the low-noise setting into the excess risk bound to achieve the optimistic bound as $O(1/n)$, where $n$ is the sample size.
title Stability-based Generalization Analysis of Randomized Coordinate Descent for Pairwise Learning
topic Machine Learning
url https://arxiv.org/abs/2503.01530