On the limitations of embedding methods
| dc.contributor.author | Mendelson, Shahar | |
| dc.date.accessioned | 2015-12-13T23:04:18Z | |
| dc.date.available | 2015-12-13T23:04:18Z | |
| dc.date.issued | 2005 | |
| dc.date.updated | 2015-12-12T07:55:15Z | |
| dc.description.abstract | We show that for any class of functions H which has a reasonable combinatorial dimension, the vast majority of small subsets of the combinatorial cube can not be represented as a Lipschitz image of a subset of H, unless the Lipschitz constant is very larg | |
| dc.identifier.issn | 0302-9743 | |
| dc.identifier.uri | http://hdl.handle.net/1885/85311 | |
| dc.publisher | Springer | |
| dc.source | Lecture Notes in Computer Science (LNCS) | |
| dc.subject | Keywords: Classification (of information); Problem solving; Classification problems; Combinatorial dimension; Lipschitz image; Lipschitz loss; Embedded systems | |
| dc.title | On the limitations of embedding methods | |
| dc.type | Journal article | |
| local.bibliographicCitation.lastpage | 365 | |
| local.bibliographicCitation.startpage | 353 | |
| local.contributor.affiliation | Mendelson, Shahar, College of Physical and Mathematical Sciences, ANU | |
| local.contributor.authoruid | Mendelson, Shahar, u4011413 | |
| local.description.notes | Imported from ARIES | |
| local.description.refereed | Yes | |
| local.identifier.absfor | 080199 - Artificial Intelligence and Image Processing not elsewhere classified | |
| local.identifier.ariespublication | MigratedxPub13653 | |
| local.identifier.citationvolume | 3559 | |
| local.identifier.scopusID | 2-s2.0-26944468649 | |
| local.type.status | Published Version |