arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.05955stat.MLcs.LGstat.ME
收藏

条件核均值嵌入的递归估计

Recursive Estimation of Conditional Kernel Mean Embeddings

Institute for Computer Science and Control (SZTAKI)(计算机科学与控制研究所(SZTAKI));Eötvös Loránd University (ELTE)(厄特沃什·罗兰大学(ELTE))

Ambrus Tamás, Balázs Csanád Csáji

AI总结:

本文提出一种在Bochner空间中递归估计条件核均值映射的新算法,将Stone定理推广到局部紧波兰空间上的希尔伯特空间值回归,证明了弱与强L2一致性并给出强渐近界,在欧氏空间、黎曼流形和函数空间子集上验证了效果。

摘要:

核均值嵌入是机器学习中一种广泛使用的技术,它将概率分布映射到再生核希尔伯特空间(RKHS)中的元素。对于监督学习问题,在观测到输入-输出对的情况下,给定输入时输出的条件分布是一个关键对象。依赖于输入的输出条件分布可以用一个RKHS值函数来编码,即条件核均值映射。本文提出了一种新的递归算法,用于在希尔伯特空间值的$L_2$空间(即Bochner空间)中估计条件核均值映射。我们在温和条件下证明了该递归估计量的弱$L_2$一致性和强$L_2$一致性。其核心思想是将Stone定理推广到局部紧波兰空间中的希尔伯特空间值回归。我们给出了关于条件核均值嵌入的新见解,并针对所提递归方法的收敛性给出了强渐近界。最后,在三个应用领域展示了结果:输入分别来自欧几里得空间、黎曼流形和函数空间的局部紧子集。

英文摘要:

Kernel mean embeddings, a widely used technique in machine learning, map probability distributions to elements of a reproducing kernel Hilbert space (RKHS). For supervised learning problems, where input-output pairs are observed, the conditional distribution of outputs given the inputs is a key object. The input dependent conditional distribution of an output can be encoded with an RKHS valued function, the conditional kernel mean map. In this paper we present a new recursive algorithm to estimate the conditional kernel mean map in a Hilbert space valued $L_2$ space, that is in a Bochner space. We prove the weak and strong $L_2$ consistency of our recursive estimator under mild conditions. The idea is to generalize Stone's theorem for Hilbert space valued regression in a locally compact Polish space. We present new insights about conditional kernel mean embeddings and give strong asymptotic bounds regarding the convergence of the proposed recursive method. Finally, the results are demonstrated on three application domains: for inputs coming from Euclidean spaces, Riemannian manifolds and locally compact subsets of function spaces.

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。

↑