| dc.contributor.author |
Antos, A |
en |
| dc.date.accessioned |
2014-06-06T06:46:21Z |
|
| dc.date.available |
2014-06-06T06:46:21Z |
|
| dc.date.issued |
2005 |
en |
| dc.identifier.uri |
http://dx.doi.org/10.1007/11503415_36 |
en |
| dc.identifier.uri |
http://62.217.125.90/xmlui/handle/123456789/2949 |
|
| dc.subject |
Discrete Distribution |
en |
| dc.subject |
Vector Quantizer |
en |
| dc.subject |
Independent and Identically Distributed |
en |
| dc.subject |
Lower Bound |
en |
| dc.title |
Improved Minimax Bounds on the Test and Training Distortion of Empirically Designed Vector Quantizers |
en |
| heal.type |
journalArticle |
en |
| heal.identifier.primary |
10.1007/11503415_36 |
en |
| heal.publicationDate |
2005 |
en |
| heal.abstract |
It is shown by earlier results that the minimax expected (test) distortion redundancy of empirical vector quantizers with three or more levels designed from n independent and identically distributed data points is at least W</font>(1/Ö</font>n)\Omega(1/\sqrt n) for the class of distributions on a bounded set. In this paper, a much simpler construction and proof for this are given |
en |
| heal.journalName |
IEEE Transactions on Information Theory |
en |
| dc.identifier.doi |
10.1007/11503415_36 |
en |