A Bayesian Wilcoxon signed-rank test based on the Dirichlet process (Contributo in atti di convegno)

Type

• Prodotto della ricerca (Classe)
• Contributo in atti di convegno (Classe)

Label

• A Bayesian Wilcoxon signed-rank test based on the Dirichlet process (Contributo in atti di convegno) (literal)

Anno

• 2014-01-01T00:00:00+01:00 (literal)

Alternative label

• Benavoli, Alessio; Mangili, Francesca; Corani, Giorgio; Zaffalon, Marco; Ruggeri, Fabrizio (2014)
  A Bayesian Wilcoxon signed-rank test based on the Dirichlet process
  in ICML 2014- 31st International Conference on Machine Learning, Beijing, China, 21-26 giugno 2014
  (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori

• Benavoli, Alessio; Mangili, Francesca; Corani, Giorgio; Zaffalon, Marco; Ruggeri, Fabrizio (literal)

Pagina inizio

• 2703 (literal)

Pagina fine

• 2713 (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#url

• http://www.jmlr.org/proceedings/papers/v32/ (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#titoloVolume

• Proceedings of The 31st International Conference on Machine Learning (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#volumeInCollana

• 32 (literal)

Note

• Scopu (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni

• IPG IDSIA, Manno, Switzerland; CNR IMATI, Milano, Italy (literal)

Titolo

• A Bayesian Wilcoxon signed-rank test based on the Dirichlet process (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#isbn

• 9781634393973 (literal)

Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#curatoriVolume

• Eric P. Xing, Tony Jebara (literal)

Abstract

• Bayesian methods are ubiquitous in machine learning. Nevertheless, the analysis of empirical results is typically performed by frequentist tests. This implies dealing with null hypothesis significance tests and p-values, even though the shortcomings of such methods are well known. We propose a nonparametric Bayesian version of the Wilcoxon signed-rank test using a Dirichlet process (DP) based prior. We address in two different ways the problem of how to choose the infinite dimensional parameter that characterizes the DP. The proposed test has all the traditional strengths of the Bayesian approach; for instance, unlike the frequentist tests, it allows verifying the null hypothesis, not only rejecting it, and taking decisions which minimize the expected loss. Moreover, one of the solutions proposed to model the infinite-dimensional parameter of the DP allows isolating instances in which the traditional frequentist test is guessing at random. We show results dealing with the comparison of two classifiers using real and simulated data. (literal)

Prodotto di

• Modellizzazione di sistemi stocastici (ICT.P11.009.001) (Modulo)
• Institute for applied mathematics and information technologies (IMATI) (Istituto)

Autore CNR

• FABRIZIO RUGGERI (Unità di personale interno)

Incoming links:

Prodotto

• Institute for applied mathematics and information technologies (IMATI) (Istituto)
• Modellizzazione di sistemi stocastici (ICT.P11.009.001) (Modulo)

Autore CNR di

• FABRIZIO RUGGERI (Unità di personale interno)