In this short paper, the trade-off between the number of labeled examples in linear regression and their precision of supervision is investigated and optimized, for the case in which distinct examples can be associated with one among M > 2 different supervision times, and weighted least squares is used for learning. The analysis extends the one made in one section of Gnecco and Nutarelli, Optimization Letters, 2019, https://doi.org/10.1007/s11590-019-01486-x , which was limited to the case M = 2. The results show that, for the specific learning problem, there is no advantage in applying weighted least squares instead of ordinary least squares as the learning algorithm.

On the optimal generalization error for weighted least squares under variable individual supervision times

Giorgio Gnecco
2021

Abstract

In this short paper, the trade-off between the number of labeled examples in linear regression and their precision of supervision is investigated and optimized, for the case in which distinct examples can be associated with one among M > 2 different supervision times, and weighted least squares is used for learning. The analysis extends the one made in one section of Gnecco and Nutarelli, Optimization Letters, 2019, https://doi.org/10.1007/s11590-019-01486-x , which was limited to the case M = 2. The results show that, for the specific learning problem, there is no advantage in applying weighted least squares instead of ordinary least squares as the learning algorithm.
978-3-030-86841-3
Optimal M-tuple of supervision times, linear regression, variance control, weighted least squares, large-sample approximation of the generalization error
File in questo prodotto:
File Dimensione Formato  
AIRO_Springer_final_Gnecco.pdf

non disponibili

Tipologia: Documento in Post-print
Licenza: Nessuna licenza
Dimensione 115.14 kB
Formato Adobe PDF
115.14 kB Adobe PDF   Visualizza/Apri   Richiedi una copia

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: http://hdl.handle.net/20.500.11771/21081
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
social impact