Bipartite ranking is an important supervised learning problem; however, unlike regression or classification, it has a quadratic dependence on the number of samples. To circumvent the prohibitive sample cost, many recent work focus on stochastic gradient-based methods. In this paper we consider an alternative approach, which leverages the structure of the widely-adopted pairwise squared loss, to obtain a stochastic and low cost algorithm that does not require stochastic gradients or learning rates. Using a novel uniform risk bound---based on matrix and vector concentration inequalities---we show that the sample size required for competitive performance against the all-pairs batch algorithm does not have a quadratic dependence. Generalization bounds for both the batch and low cost stochastic algorithms are presented. Experimental results show significant speed gain against the batch algorithm, as well as competitive performance against state-of-the-art bipartite ranking algorithms on real datasets.
Surrogate Regret Bounds for Bipartite Ranking via Strongly Proper Losses
Indian Institute of Science(印度科学学院)
二分排名问题,其中实例被标记为正面或负面,目标是学习一个评分函数,该函数最大限度地减少对一对正面和负面实例的错误排名概率(或等效地,最大化ROC曲线下的面积),近年来已被广泛研究。一个占主导地位的理论和算法框架的问题已经减少二分排名成对分类,特别是,它是众所周知的,二分排名遗憾可以制定成对分类遗憾,这反过来又可以使用通常的遗憾界分类问题的上限。最近,Kotlowski et al.(2011)根据与标准(非成对)逻辑和指数损失的平衡版本相关的遗憾,显示了二分排序的遗憾界限。在本文中,我们表明,这种(非成对)代理遗憾界的二分排名可以得到一个广泛的类适当的(复合)损失,我们的术语作为强适当的。我们的证明技术比Kotlowski等人(2011)简单得多,并且依赖于Reid和Williamson(2010,2011)和其他人最近阐明的适当(复合)损失的性质。我们的结果产生明确的代理边界(没有隐藏的平衡条款)在各种强适当的损失,包括例如逻辑,指数,平方和平方铰链损失的特殊情况。我们还通过Clemencon和Robbiano(2011)的最新结果在某些低噪声条件下获得了更紧密的代理边界。
Colorado State University(科罗拉多州立大学);Fort Collins, USA(美国科罗拉多州科林斯堡(此处仅作说明,按要求机构粒度为大学级别,原机构为Colorado State University,Fort Collins, USA是其所在城市和国家,按要求提取到大学级别即可,故主要机构为Colorado State University,Fort Collins, USA作为补充说明,但严格按要求,机构名称应为Colorado State University,Fort Collins, USA?但根据示例,原机构是Colorado State University, Fort Collins, USA,所以正确提取应为:{)
A comparative study on feature selection for a risk prediction model for colorectal cancer
Catalan Institute of Oncology-IDIBELL(加泰罗尼亚肿瘤研究所-IDIBELL);University of Barcelona(巴塞罗那大学);Public Health Division, Department of Health of Madrid(马德里卫生部公共卫生司)
Top-K Pairwise Ranking: Bridging the Gap Among Ranking-Based Measures for Multi-Label Classification
IIE, Chinese Academy of Sciences(中国科学院自动化研究所);SCS, University of Chinese Academy of Sciences(中国科学院大学计算机科学与技术学院);IIP, ICT, Chinese Academy of Sciences(中国科学院计算技术研究所);SCST, University of Chinese Academy of Sciences(中国科学院大学计算机科学与技术学院);Alibaba Group(阿里巴巴集团);SCST, Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区计算机科学与技术学院);BDKM, University of Chinese Academy of Sciences(中国科学院大学大数据与知识管理实验室)
L1-regularized neural ranking for risk stratification and its application to prediction of time to distant metastasis in luminal node negative chemotherapy naïve breast cancer patients
ROC曲线下面积(Area under ROC,AUC)是二分类和二分排序问题的重要度量。然而,很难直接优化AUC作为学习目标,所以大多数现有的算法是基于优化替代损失AUC。这些替代损失的一个显著缺点是,它们需要在训练数据之间进行成对比较,这导致运行时间缓慢,并增加了在线学习的本地存储。在这项工作中,我们描述了一个新的替代损失的基础上重新制定的AUC风险,这不需要成对比较,但排名的预测。我们进一步表明,可以避免排名操作,并根据此代理获得的学习目标在时间和存储上具有线性复杂度。我们进行实验,以证明在线和批量算法的有效性AUC优化建议的替代损失的基础上。
Feature Ranking in Credit-Risk with Qudit-Based Networks
Department of Informatics and Telecommunications(信息与电信系);National and Kapodistrian University of Athens(国家与卡布里亚大学);Eulambia Advanced Technologies Ltd(Eulambia先进技术有限公司)
Industrial Engineering and Operations Research, Columbia University(哥伦比亚大学工业工程与运筹学系);School of Computing, National University of Singapore(新加坡国立大学计算机学院)