http://www.cnr.it/ontology/cnr/individuo/prodotto/ID171602
A deterministic learning approach based on discrepancy (Articolo in rivista)
- Type
- Label
- A deterministic learning approach based on discrepancy (Articolo in rivista) (literal)
- Anno
- 2003-01-01T00:00:00+01:00 (literal)
- Alternative label
- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#autori
- C. Cervellera, M. Muselli (literal)
- Pagina inizio
- Pagina fine
- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#numeroVolume
- Rivista
- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#note
- Apolloni, Bruno; Marinaro, Maria; Tagliaferri, Roberto (Eds.) (literal)
- Note
- ISI Web of Science (WOS) (literal)
- Scopu (literal)
- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#affiliazioni
- C. Cervellera: CNR-ISSIA, Genova, Italy;
M. Muselli: CNR-IEIIT, Genova, Italy. (literal)
- Titolo
- A deterministic learning approach based on discrepancy (literal)
- Abstract
- The general problem of reconstructing an unknown function from a
finite collection of samples is considered, in case the position of
each input vector in the training set is not fixed beforehand, but is
part of the learning process. In particular, the consistency of the
Empirical Risk Minimization (ERM) principle is analyzed, when the
points in the input space are generated by employing a purely
deterministic algorithm (deterministic learning).
When the output generation is not subject to noise, classical
number-theoretic results, involving discrepancy and variation, allow
to establish a sufficient condition for the consistency of the ERM
principle. In addition, the adoption of low-discrepancy sequences
permits to achieve a learning rate of O(1/L), being L the size of
the training set. An extension to the noisy case is discussed. (literal)
- Prodotto di
- Autore CNR
- Insieme di parole chiave
Incoming links:
- Prodotto
- Autore CNR di
- Http://www.cnr.it/ontology/cnr/pubblicazioni.owl#rivistaDi
- Insieme di parole chiave di
