Aggregation via Empirical risk minimization
| dc.contributor.author | Mendelson, Shahar | |
| dc.contributor.author | Lecue, Guillaume | |
| dc.date.accessioned | 2015-12-08T22:40:21Z | |
| dc.date.available | 2015-12-08T22:40:21Z | |
| dc.date.issued | 2009 | |
| dc.date.updated | 2015-12-08T10:22:50Z | |
| dc.description.abstract | Given a finite set F of estimators, the problem of aggregation is to construct a new estimator whose risk is as close as possible to the risk of the best estimator in F. It was conjectured that empirical minimization performed in the convex hull of F is an optimal aggregation method, but we show that this conjecture is false. Despite that, we prove that empirical minimization in the convex hull of a well chosen, empirically determined subset of F is an optimal aggregation method. | |
| dc.identifier.issn | 0178-8051 | |
| dc.identifier.uri | http://hdl.handle.net/1885/36461 | |
| dc.publisher | Springer | |
| dc.source | Probability Theory and Related Fields | |
| dc.title | Aggregation via Empirical risk minimization | |
| dc.type | Journal article | |
| local.bibliographicCitation.lastpage | 613 | |
| local.bibliographicCitation.startpage | 591 | |
| local.contributor.affiliation | Mendelson, Shahar, College of Physical and Mathematical Sciences, ANU | |
| local.contributor.affiliation | Lecue, Guillaume, College of Physical and Mathematical Sciences, ANU | |
| local.contributor.authoruid | Mendelson, Shahar, u4011413 | |
| local.contributor.authoruid | Lecue, Guillaume, u4762074 | |
| local.description.notes | Imported from ARIES | |
| local.identifier.absfor | 010101 - Algebra and Number Theory | |
| local.identifier.ariespublication | u9209279xPUB136 | |
| local.identifier.citationvolume | 145 | |
| local.identifier.doi | 10.1007/s00440-008-0180-8 | |
| local.identifier.scopusID | 2-s2.0-70350012166 | |
| local.type.status | Published Version |