BriefGPT.xyz
Mar, 2015
带特化线性分类器的领域适应的 PAC-Bayesian 定理
PAC-Bayesian Theorems for Domain Adaptation with Specialization to Linear Classifiers
HTML
PDF
Pascal Germain, Amaury Habrard, François Laviolette, Emilie Morvant
TL;DR
本文在PAC-Bayesian理论中提供了两个主要方面的贡献，分别是基于新的分布伪距离提供一个更紧的PAC-Bayesian领域适应性边缘；另外实现了对多源领域适应性的推广。
Abstract
In this paper, we provide two main contributions in
pac-bayesian theory
for
domain adaptation
where the objective is to learn, from a
source dist
→