Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Mario Beraha"'
Autor:
Matteo Pegoraro, Mario Beraha
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 35:9342-9349
We address the problem of performing Principal Component Analysis over a family of probability measures on the real line, using the Wasserstein geometry. We present a novel representation of the 2-Wasserstein space, based on a well known isometric bi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b2e060cc2cb40719d3b875aaa12c6078
https://doi.org/10.1609/aaai.v35i10.17126
https://doi.org/10.1609/aaai.v35i10.17126
Assessing homogeneity of distributions is an old problem that has received considerable attention, especially in the nonparametric Bayesian literature. To this effect, we propose the semi-hierarchical Dirichlet process, a novel hierarchical prior tha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::581db5373b0f366e1ec8858b9d82a2eb
http://hdl.handle.net/11585/835887
http://hdl.handle.net/11585/835887
We consider the problem of spatially dependent areal data, where for each area independent observations are available, and propose to model the density of each area through a finite mixture of Gaussian distributions. The spatial dependence is introdu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cc87cda803d91a5a36a3d5797e36b758
http://arxiv.org/abs/2007.14961
http://arxiv.org/abs/2007.14961
Publikováno v:
Beraha, M, Argiento, R, Møller, J & Guglielmi, A 2020, ' MCMC computations for Bayesian mixture models using repulsive point processes. ', arXiv.org (e-prints) . < https://arxiv.org/abs/2011.06444 >
Aalborg University
Aalborg University
Repulsive mixture models have recently gained popularity for Bayesian cluster detection. Compared to more traditional mixture models, repulsive mixture models produce a smaller number of well-separated clusters. The most commonly used methods for pos
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::6c6aa74a7584f7017d628c0cef07adaf
Publikováno v:
IJCNN
Mutual information has been successfully adopted in filter feature-selection methods to assess both the relevancy of a subset of features in predicting the target variable and the redundancy with respect to other variables. However, existing algorith
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::275915e082259b93ed22284d88f76c76
http://arxiv.org/abs/1907.07384
http://arxiv.org/abs/1907.07384