arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1912.00537cs.LGstat.ML
收藏

低成本二部排序的风险界

Risk Bounds for Low Cost Bipartite Ranking

San Gultekin, John Paisley

摘要:

二分排序是一个重要的监督学习问题;然而,与回归或分类不同,它对样本数量有二次依赖性。为了避免过高的样本成本,许多最近的工作集中在随机梯度为基础的方法。在本文中,我们考虑一种替代方法,它利用广泛采用的成对平方损失的结构,以获得一个随机和低成本的算法,不需要随机梯度或学习率。使用一种新的统一的风险界-基于矩阵和向量浓度不等式-我们表明,对所有对批处理算法的竞争性能所需的样本量不具有二次依赖。批量和低成本随机算法的推广界。实验结果表明,显着的速度增益对批处理算法,以及竞争力的性能对国家的最先进的二分排名算法在真实的数据集。

英文摘要:

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.

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。

↑