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 0710.2889cs.LGcs.IR
收藏

排序到分类的有效约简

An efficient reduction of ranking to classification

Google Research(谷歌研究院);Courant Institute of Mathematical Sciences(库朗数学科学研究所)

Nir Ailon, Mehryar Mohri

摘要:

本文描述了一个有效的减少学习问题的排名二进制分类。减少保证了平均成对误排序遗憾的最多的二元分类器的遗憾,改善了最近的结果Balcan等人,它只保证了一个因素2。此外,我们的减少适用于一个更广泛的类的排名损失函数,承认一个更简单的证明,和预期的运行时间复杂度性,我们的算法在调用分类器或偏好函数的数量方面的改进,从$Ω(n^2)$到$O(n \log n)$。此外,当只需要$k$排名靠前的元素($k \ll n$)时,如在信息抽取或搜索引擎中的许多应用中,我们的算法的时间复杂度可以进一步降低到$O(k \log k + n)$。因此,我们的减少和算法是实际的实际应用中的点数排名超过几千。我们的许多结果也超出了以前研究的二分情况。我们的预测是随机的。为了补充我们的结果,我们还推导出任何确定性减少二进制(偏好)分类排名的下限,这意味着我们使用的随机减少是必要的,我们提供的保证。

英文摘要:

This paper describes an efficient reduction of the learning problem of ranking to binary classification. The reduction guarantees an average pairwise misranking regret of at most that of the binary classifier regret, improving a recent result of Balcan et al which only guarantees a factor of 2. Moreover, our reduction applies to a broader class of ranking loss functions, admits a simpler proof, and the expected running time complexity of our algorithm in terms of number of calls to a classifier or preference function is improved from $Ω(n^2)$ to $O(n \log n)$. In addition, when the top $k$ ranked elements only are required ($k \ll n$), as in many applications in information extraction or search engines, the time complexity of our algorithm can be further reduced to $O(k \log k + n)$. Our reduction and algorithm are thus practical for realistic applications where the number of points to rank exceeds several thousands. Much of our results also extend beyond the bipartite case previously studied. Our rediction is a randomized one. To complement our result, we also derive lower bounds on any deterministic reduction from binary (preference) classification to ranking, implying that our use of a randomized reduction is essentially necessary for the guarantees we provide.

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。

↑