We study the generalization properties of ridge regression with random features in the statistical learning framework. We show for the first time that O(1/ √ n) learning bounds can be achieved with only O( √ n log n) random features rather than O(n) as suggested by previous results. Further, we prove faster learning rates and show that they might require more random features, unless they are sampled according to a possibly problem dependent distribution. Our results shed light on the statistical computational trade-offs in large scale kernelized learning, showing the potential effectiveness of random features in reducing the computational complexity while keeping optimal generalization properties

Generalization Properties of Learning with Random Features

Alessandro Rudi;Lorenzo Rosasco
2017-01-01

Abstract

We study the generalization properties of ridge regression with random features in the statistical learning framework. We show for the first time that O(1/ √ n) learning bounds can be achieved with only O( √ n log n) random features rather than O(n) as suggested by previous results. Further, we prove faster learning rates and show that they might require more random features, unless they are sampled according to a possibly problem dependent distribution. Our results shed light on the statistical computational trade-offs in large scale kernelized learning, showing the potential effectiveness of random features in reducing the computational complexity while keeping optimal generalization properties
File in questo prodotto:
File Dimensione Formato  
11567-888551.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: Documento in versione editoriale
Dimensione 655.55 kB
Formato Adobe PDF
655.55 kB 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/11567/888551
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 166
  • ???jsp.display-item.citation.isi??? 86
social impact