arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1301.5332stat.MLcs.LG
收藏

基于成对损失函数的在线学习

Online Learning with Pairwise Loss Functions

Tufts University(塔夫茨大学);Akamai Technologies(阿卡迈技术公司)

Yuyang Wang, Roni Khardon, Dmitry Pechyony, Rosie Jones

摘要:

具有成对损失函数的有效在线学习是构建大规模学习系统的关键组成部分,该系统最大化了受试者操作特征(ROC)曲线下的面积。在本文中,我们研究的推广性能的在线学习算法与成对损失函数。我们表明,现有的证明技术的泛化界的在线算法的单变量损失不能直接适用于成对损失。在本文中,我们得出的第一个结果提供数据依赖的边界的序列中产生的假设的平均风险的一个任意的在线学习者在一个容易计算的统计,并展示如何提取一个低风险的假设序列。我们证明了我们的结果的一般性,将其应用到机器学习中的两个重要问题。首先,我们分析了两个在线算法的二分排名,一个是感知器算法的自然扩展,另一个使用在线凸优化。其次,我们提供了一个有监督的度量学习的在线算法的风险界的分析。

英文摘要:

Efficient online learning with pairwise loss functions is a crucial component in building large-scale learning system that maximizes the area under the Receiver Operator Characteristic (ROC) curve. In this paper we investigate the generalization performance of online learning algorithms with pairwise loss functions. We show that the existing proof techniques for generalization bounds of online algorithms with a univariate loss can not be directly applied to pairwise losses. In this paper, we derive the first result providing data-dependent bounds for the average risk of the sequence of hypotheses generated by an arbitrary online learner in terms of an easily computable statistic, and show how to extract a low risk hypothesis from the sequence. We demonstrate the generality of our results by applying it to two important problems in machine learning. First, we analyze two online algorithms for bipartite ranking; one being a natural extension of the perceptron algorithm and the other using online convex optimization. Secondly, we provide an analysis for the risk bound for an online algorithm for supervised metric learning.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑