Fast two-sample testing with analytic representations of probability measures
We propose a class of nonparametric two-sample tests with a cost linear in the sample size. Two tests are given, both based on an ensemble of distances between analytic functions representing each of the distributions. The first test uses smoothed empirical characteristic functions to represent the...
Главные авторы: | Chwialkowski, K, Ramdas, A, Sejdinovic, D, Gretton, A |
---|---|
Формат: | Conference item |
Опубликовано: |
Massachusetts Institute of Technology Press
2015
|
Схожие документы
-
Optimal kernel choice for large-scale two-sample tests
по: Gretton, A, и др.
Опубликовано: (2012) -
A kernel test for three-variable interactions
по: Sejdinovic, D, и др.
Опубликовано: (2013) -
Large-scale kernel methods for independence testing
по: Zhang, Q, и др.
Опубликовано: (2017) -
Hypothesis testing using pairwise distances and associated kernels
по: Sejdinovic, D, и др.
Опубликовано: (2012) -
A kernel log-rank test of independence for right-censored data
по: Fernández, T, и др.
Опубликовано: (2021)