In this paper we discuss the Spectral Support Estimation algorithm (De Vito et al., 2010) by analyzing its 27 geometrical and computational properties. The estimator is non-parametric and the model selection 28 depends on three parameters whose role is clarified by simulations on a two-dimensional space. The performance of the algorithm for novelty detection is tested and compared with its main competitors on a 30 collection of real benchmark datasets of different sizes and types.
Geometrical and computational aspects of Spectral Support Estimation for novelty detection
DE VITO, ERNESTO;ODONE, FRANCESCA
2014-01-01
Abstract
In this paper we discuss the Spectral Support Estimation algorithm (De Vito et al., 2010) by analyzing its 27 geometrical and computational properties. The estimator is non-parametric and the model selection 28 depends on three parameters whose role is clarified by simulations on a two-dimensional space. The performance of the algorithm for novelty detection is tested and compared with its main competitors on a 30 collection of real benchmark datasets of different sizes and types.
File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
