Kernel Two-Sample and Independence Tests for Nonstationary Random Processes

  title={Kernel Two-Sample and Independence Tests for Nonstationary Random Processes},
  author={Felix Laumann and Julius von K{\"u}gelgen and Mauricio Barahona},
  journal={Engineering Proceedings},
Two-sample and independence tests with the kernel-based mmd and hsic have shown remarkable results on i.i.d. data and stationary random processes. However, these statistics are not directly applicable to nonstationary random processes, a prevalent form of data in many scientific disciplines. In this work, we extend the application of mmd and hsic to nonstationary settings by assuming access to independent realisations of the underlying random process. These realisations—in the form of… Expand

Figures and Tables from this paper


A Kernel Two-Sample Test
This work proposes a framework for analyzing and comparing distributions, which is used to construct statistical tests to determine if two samples are drawn from different distributions, and presents two distribution free tests based on large deviation bounds for the maximum mean discrepancy (MMD). Expand
Large-scale kernel methods for independence testing
This contribution provides an extensive study of the use of large-scale kernel approximations in the context of independence testing, contrasting block-based, Nyström and random Fourier feature approaches and demonstrates that the methods give comparable performance with existing methods while using significantly less computation time and memory. Expand
A Fast, Consistent Kernel Two-Sample Test
A novel estimate of the null distribution is computed, computed from the eigen-spectrum of the Gram matrix on the aggregate sample from P and Q, and having lower computational cost than the bootstrap. Expand
Applications of distance correlation to time series
The use of empirical characteristic functions for inference problems, including estimation in some special parametric settings and testing for goodness of fit, has a long history dating back to theExpand
Statistical analysis of coupled time series with Kernel Cross-Spectral Density operators
A general framework for the statistical analysis of dependencies when random variables are sampled from stationary time-series of arbitrary objects is provided and an independence test between time series is developed, as well as a similarity measure to compare different types of coupling. Expand
A Kernel Method for the Two-Sample-Problem
This work proposes two statistical tests to determine if two samples are from different distributions, and applies this approach to a variety of problems, including attribute matching for databases using the Hungarian marriage method, where the test performs strongly. Expand
A Wild Bootstrap for Degenerate Kernel Tests
A wild bootstrap method for nonparametric hypothesis tests based on kernel distribution embeddings is proposed, used to construct provably consistent tests that apply to random processes, for which the naive permutation-based bootstrap fails. Expand
A Kernel Statistical Test of Independence
A novel test of the independence hypothesis for one particular kernel independence measure, the Hilbert-Schmidt independence criterion (HSIC), which outperforms established contingency table and functional correlation-based tests, and is greater for multivariate data. Expand
Independence test and canonical correlation analysis based on the alignment between kernel matrices for multivariate functional data
This paper constructed independence test and nonlinear canonical variables for multivariate functional data and shows that using functional variants of the proposed measures, they obtain much better results in recognizing nonlinear dependence. Expand
Estimation of the mean of functional time series and a two-sample problem
Summary. The paper is concerned with inference based on the mean function of a functional time series. We develop a normal approximation for the functional sample mean and then focus on theExpand