In many real world applications, the number of examples to learn from is plentiful, but we can only obtain limited information on each individual example. We study the possibilities of efficient, provably correct, large-scale learning in such settings. The main theme we would like to establish is that large amounts of examples can compensate for the lack of full information on each individual example. The type of partial information we consider can be due to inherent noise or from constraints on the type of interaction with the data source. In particular, we describe and analyze algorithms for budgeted learning, in which the learner can only view a few attributes of each training example (Cesa-Bianchi, Shalev-Shwartz, and Shamir 2010a; 2010c), and algorithms for learning kernel-based predictors, when individual examples are corrupted by random noise (Cesa-Bianchi, Shalev-Shwartz, and Shamir 2010b).

Quantity makes quality: learning with partial views / N. Cesa-Bianchi, S. Shalev Shwartz, O. Shamir - In: Proceedings of the twenty-fifth AAAI conference on artificial intelligenceMenlo Park, CA, USA : AAAI Press, 2011. - ISBN 9781577355076. - pp. 1547-1550 (( Intervento presentato al 25th. convegno AAAI Conference on Artificial Intelligence tenutosi a San Francisco nel 2011.

Quantity makes quality: learning with partial views

N. Cesa-Bianchi
Primo
;
2011

Abstract

In many real world applications, the number of examples to learn from is plentiful, but we can only obtain limited information on each individual example. We study the possibilities of efficient, provably correct, large-scale learning in such settings. The main theme we would like to establish is that large amounts of examples can compensate for the lack of full information on each individual example. The type of partial information we consider can be due to inherent noise or from constraints on the type of interaction with the data source. In particular, we describe and analyze algorithms for budgeted learning, in which the learner can only view a few attributes of each training example (Cesa-Bianchi, Shalev-Shwartz, and Shamir 2010a; 2010c), and algorithms for learning kernel-based predictors, when individual examples are corrupted by random noise (Cesa-Bianchi, Shalev-Shwartz, and Shamir 2010b).
Settore INF/01 - Informatica
2011
Book Part (author)
File in questo prodotto:
File Dimensione Formato  
2011_aaai_cesshalsham.pdf

accesso aperto

Tipologia: Publisher's version/PDF
Dimensione 208.92 kB
Formato Adobe PDF
208.92 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

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/2434/160356
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 0
  • ???jsp.display-item.citation.isi??? ND
social impact