BriefGPT.xyz
Nov, 2011
UPAL: 无偏的基于池的主动学习
UPAL: Unbiased Pool Based Active Learning
HTML
PDF
Ravi Ganti, Alexander Gray
TL;DR
本文提出了一种名为UPAL的算法，通过最小化线性分类器假设空间中偏差估计来解决基于池的主动学习问题，利用最近关于随机矩阵谱的结果，将其等价于指数加权平均预测器，在与Vowpal Wabbit的主动学习实现和先前提出的基于池的主动学习实现进行实证比较后显示出良好的性能和可伸缩性。
Abstract
In this paper we address the problem of
pool based active learning
, and provide an algorithm, called UPAL, that works by minimizing the unbiased estimator of the risk of a hypothesis in a given hypothesis space. For the space of
→