arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1405.0110math.PRmath.FAmath.STstat.MLstat.TH
收藏

无坐标统计的结构化方法

A Structural Approach to Coordinate-Free Statistics

Tom LaGatta, P. Richard Hahn

摘要:

我们考虑一般拓扑向量空间中的学习问题。通过利用已知的(或参数化的)协方差结构,我们的主要定理证明了任何连续线性映射对应于嵌入的希尔伯特空间的某个同构。通过反转这个同构和连续扩展,我们构造了一个版本的普通最小二乘估计绝对的一般性。我们的Gauss-Markov定理证明了OLS是一个“最佳线性无偏估计”,推广了经典结果。我们构造了一个随机版本的OLS估计,这是一个连续的解体,正是类“不相关意味着独立”(UII)的措施。因此,高斯测度总是通过连续线性映射表现出连续的分解,从而推广了第一作者的一个定理。将这个框架应用于机器学习中的一些问题,我们证明了协方差张量的一个有用的表示定理,并证明了OLS定义了一个很好的克里金预测一般索引空间上的向量值数组。我们还构建了一个支持向量机分类器在这种设置。我们希望我们的文章能够揭示概率论、统计学和机器学习之间的一些更深层次的联系,并可能成为这三个社区的交点。

英文摘要:

We consider the question of learning in general topological vector spaces. By exploiting known (or parametrized) covariance structures, our Main Theorem demonstrates that any continuous linear map corresponds to a certain isomorphism of embedded Hilbert spaces. By inverting this isomorphism and extending continuously, we construct a version of the Ordinary Least Squares estimator in absolute generality. Our Gauss-Markov theorem demonstrates that OLS is a "best linear unbiased estimator", extending the classical result. We construct a stochastic version of the OLS estimator, which is a continuous disintegration exactly for the class of "uncorrelated implies independent" (UII) measures. As a consequence, Gaussian measures always exhibit continuous disintegrations through continuous linear maps, extending a theorem of the first author. Applying this framework to some problems in machine learning, we prove a useful representation theorem for covariance tensors, and show that OLS defines a good kriging predictor for vector-valued arrays on general index spaces. We also construct a support-vector machine classifier in this setting. We hope that our article shines light on some deeper connections between probability theory, statistics and machine learning, and may serve as a point of intersection for these three communities.

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。

↑