Composite Goodness-of-fit Tests with Kernels

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Key, Oscar, Gretton, Arthur, Briol, François-Xavier, Fernandez, Tamara
Formato: Preprint
Publicado: 2021
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909584877158400
author Key, Oscar
Gretton, Arthur
Briol, François-Xavier
Fernandez, Tamara
author_facet Key, Oscar
Gretton, Arthur
Briol, François-Xavier
Fernandez, Tamara
contents Model misspecification can create significant challenges for the implementation of probabilistic models, and this has led to development of a range of robust methods which directly account for this issue. However, whether these more involved methods are required will depend on whether the model is really misspecified, and there is a lack of generally applicable methods to answer this question. In this paper, we propose one such method. More precisely, we propose kernel-based hypothesis tests for the challenging composite testing problem, where we are interested in whether the data comes from any distribution in some parametric family. Our tests make use of minimum distance estimators based on the maximum mean discrepancy and the kernel Stein discrepancy. They are widely applicable, including whenever the density of the parametric model is known up to normalisation constant, or if the model takes the form of a simulator. As our main result, we show that we are able to estimate the parameter and conduct our test on the same data (without data splitting), while maintaining a correct test level. Our approach is illustrated on a range of problems, including testing for goodness-of-fit of an unnormalised non-parametric density model, and an intractable generative model of a biological cellular network.
format Preprint
id arxiv_https___arxiv_org_abs_2111_10275
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle Composite Goodness-of-fit Tests with Kernels
Key, Oscar
Gretton, Arthur
Briol, François-Xavier
Fernandez, Tamara
Machine Learning
Methodology
Model misspecification can create significant challenges for the implementation of probabilistic models, and this has led to development of a range of robust methods which directly account for this issue. However, whether these more involved methods are required will depend on whether the model is really misspecified, and there is a lack of generally applicable methods to answer this question. In this paper, we propose one such method. More precisely, we propose kernel-based hypothesis tests for the challenging composite testing problem, where we are interested in whether the data comes from any distribution in some parametric family. Our tests make use of minimum distance estimators based on the maximum mean discrepancy and the kernel Stein discrepancy. They are widely applicable, including whenever the density of the parametric model is known up to normalisation constant, or if the model takes the form of a simulator. As our main result, we show that we are able to estimate the parameter and conduct our test on the same data (without data splitting), while maintaining a correct test level. Our approach is illustrated on a range of problems, including testing for goodness-of-fit of an unnormalised non-parametric density model, and an intractable generative model of a biological cellular network.
title Composite Goodness-of-fit Tests with Kernels
topic Machine Learning
Methodology
url https://arxiv.org/abs/2111.10275