arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1502.07229stat.MLcs.LG
收藏

带核的在线成对学习算法

Online Pairwise Learning Algorithms with Kernels

State University of New York at Albany(纽约州立大学奥尔巴尼分校);City University of Hong Kong(香港城市大学)

Yiming Ying, Ding-Xuan Zhou

摘要:

成对学习通常是指一个学习任务,它涉及到一个损失函数依赖于成对的例子,其中最显着的包括排名,度量学习和AUC最大化。在本文中,我们研究了在再生核Hilbert空间(RKHS)的无约束设置中具有最小二乘损失函数的成对学习的在线算法,我们称之为在线成对学习算法(OPERA)。现有的作品\cite{Kar,Wang},要求迭代被限制到一个有界域或损失函数是强凸的,OPERA是与一个非强凸的目标函数,并学习目标函数在一个无约束的RKHS。具体地说,我们建立了一个一般定理,保证几乎必然收敛的最后一个OPERA没有任何假设的基础上的分布。在多项式衰减步长的条件下,得到了显式的收敛速度。我们还建立了一个有趣的属性,一个家庭的广泛使用的内核设置成对学习,并说明了上述收敛结果使用这样的内核。我们的方法主要依赖于RKHS的特征,使用其相关的积分算子和概率不等式的随机变量的值在希尔伯特空间。

英文摘要:

Pairwise learning usually refers to a learning task which involves a loss function depending on pairs of examples, among which most notable ones include ranking, metric learning and AUC maximization. In this paper, we study an online algorithm for pairwise learning with a least-square loss function in an unconstrained setting of a reproducing kernel Hilbert space (RKHS), which we refer to as the Online Pairwise lEaRning Algorithm (OPERA). In contrast to existing works \cite{Kar,Wang} which require that the iterates are restricted to a bounded domain or the loss function is strongly-convex, OPERA is associated with a non-strongly convex objective function and learns the target function in an unconstrained RKHS. Specifically, we establish a general theorem which guarantees the almost surely convergence for the last iterate of OPERA without any assumptions on the underlying distribution. Explicit convergence rates are derived under the condition of polynomially decaying step sizes. We also establish an interesting property for a family of widely-used kernels in the setting of pairwise learning and illustrate the above convergence results using such kernels. Our methodology mainly depends on the characterization of RKHSs using its associated integral operators and probability inequalities for random variables with values in a Hilbert space.

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。

↑