This chapter deals with linear regression problems for which one has the possibility of varying the supervision cost per example, by controlling the conditional variance of the output given the feature vector. For a fixed upper bound on the total available supervision cost, the trade-off between the number of training examples and their precision of supervision is investigated, using a nonasymptotic data-independent bound from the literature in statistical learning theory. This bound is related to the truncated output of the ordinary least squares regression algorithm. The results of the analysis are also compared theoretically with the ones obtained in a previous work, based on a large-sample approximation of the untruncated output of ordinary least squares. Advantages and disadvantages of the investigated approach are discussed.

A Statistical Learning Theory Approach for the Analysis of the Trade-off Between Sample Size and Precision in Truncated Ordinary Least Squares

Raciti F.;
2022-01-01

Abstract

This chapter deals with linear regression problems for which one has the possibility of varying the supervision cost per example, by controlling the conditional variance of the output given the feature vector. For a fixed upper bound on the total available supervision cost, the trade-off between the number of training examples and their precision of supervision is investigated, using a nonasymptotic data-independent bound from the literature in statistical learning theory. This bound is related to the truncated output of the ordinary least squares regression algorithm. The results of the analysis are also compared theoretically with the ones obtained in a previous work, based on a large-sample approximation of the untruncated output of ordinary least squares. Advantages and disadvantages of the investigated approach are discussed.
2022
9783031008313
9783031008320
Conditional variance
Linear regression
Statistical learning theory
Supervision cost
File in questo prodotto:
File Dimensione Formato  
671ab42f-e3dc-40e8-a358-6718f239959c.pdf

solo gestori archivio

Tipologia: Versione Editoriale (PDF)
Licenza: NON PUBBLICO - Accesso privato/ristretto
Dimensione 9.82 MB
Formato Adobe PDF
9.82 MB Adobe PDF   Visualizza/Apri

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: https://hdl.handle.net/20.500.11769/606669
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact