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 1906.05591cs.LGcs.SYeess.SYstat.ML
收藏

动态回归参数学习的有限样本分析

Finite Sample Analysis Of Dynamic Regression Parameter Learning

Technion, Israel Institute of Technology(以色列理工学院)

Mark Kozdoba, Edward Moroshko, Shie Mannor, Koby Crammer

摘要:

我们考虑动态线性回归问题,其中预测向量可能随时间变化。该问题可以建模为具有非常数观测算子的线性动态系统,其中需要学习的参数是过程噪声和观测噪声的方差。虽然动态回归的方差估计是一个自然的问题,有各种各样的应用,这个问题的现有方法要么缺乏保证完全,或只有渐近保证没有明确的利率。特别是,现有的文献没有提供任何线索,以下基本问题:在数据特性方面,收敛速度取决于什么?在本文中,我们研究了全局系统算子--将噪声向量映射到输出的算子。我们得到的估计,其频谱,并作为一个结果,得出第一个已知的方差估计有限样本复杂性的保证。所提出的界限取决于与系统算子相关的某个谱的形状,从而提供了可用于约束估计误差的数据的第一个已知的明确几何参数。此外,结果适用于任意亚高斯分布的噪声项。我们评估合成和现实世界的基准的方法。

英文摘要:

We consider the dynamic linear regression problem, where the predictor vector may vary with time. This problem can be modeled as a linear dynamical system, with non-constant observation operator, where the parameters that need to be learned are the variance of both the process noise and the observation noise. While variance estimation for dynamic regression is a natural problem, with a variety of applications, existing approaches to this problem either lack guarantees altogether, or only have asymptotic guarantees without explicit rates. In particular, existing literature does not provide any clues to the following fundamental question: In terms of data characteristics, what does the convergence rate depend on? In this paper we study the global system operator -- the operator that maps the noise vectors to the output. We obtain estimates on its spectrum, and as a result derive the first known variance estimators with finite sample complexity guarantees. The proposed bounds depend on the shape of a certain spectrum related to the system operator, and thus provide the first known explicit geometric parameter of the data that can be used to bound estimation errors. In addition, the results hold for arbitrary sub Gaussian distributions of noise terms. We evaluate the approach on synthetic and real-world benchmarks.

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。

↑