Minimax rate adaptive estimation over continuous hyper-parameters

Y. Yang

doi:10.1109/18.930947

Minimax rate adaptive estimation over continuous hyper-parameters

Y. Yang

Statistics (Twin Cities)

Research output: Contribution to journal › Article › peer-review

5 Scopus citations

Abstract

We study minimax-rate adaptive estimation for density classes indexed by continuous hyper-parameters. The classes are assumed to be partially ordered in terms of inclusion relationship. Under a mild condition on the minimax risks, we show that a minimax-rate adaptive estimator can be constructed for the classes.

Original language	English (US)
Pages (from-to)	2081-2085
Number of pages	5
Journal	IEEE Transactions on Information Theory
Volume	47
Issue number	5
DOIs	https://doi.org/10.1109/18.930947
State	Published - Jul 2001

Keywords

Adaptive density estimation
Combining procedures
Minimax-rate adaptation

Publisher link

10.1109/18.930947

Find It

Find It at U of M Libraries

Cite this

@article{282f75b95f584150893949201179ef23,

title = "Minimax rate adaptive estimation over continuous hyper-parameters",

abstract = "We study minimax-rate adaptive estimation for density classes indexed by continuous hyper-parameters. The classes are assumed to be partially ordered in terms of inclusion relationship. Under a mild condition on the minimax risks, we show that a minimax-rate adaptive estimator can be constructed for the classes.",

keywords = "Adaptive density estimation, Combining procedures, Minimax-rate adaptation",

author = "Y. Yang",

year = "2001",

month = jul,

doi = "10.1109/18.930947",

language = "English (US)",

volume = "47",

pages = "2081--2085",

journal = "IEEE Transactions on Information Theory",

issn = "0018-9448",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "5",

}

TY - JOUR

T1 - Minimax rate adaptive estimation over continuous hyper-parameters

AU - Yang, Y.

PY - 2001/7

Y1 - 2001/7

N2 - We study minimax-rate adaptive estimation for density classes indexed by continuous hyper-parameters. The classes are assumed to be partially ordered in terms of inclusion relationship. Under a mild condition on the minimax risks, we show that a minimax-rate adaptive estimator can be constructed for the classes.

AB - We study minimax-rate adaptive estimation for density classes indexed by continuous hyper-parameters. The classes are assumed to be partially ordered in terms of inclusion relationship. Under a mild condition on the minimax risks, we show that a minimax-rate adaptive estimator can be constructed for the classes.

KW - Adaptive density estimation

KW - Combining procedures

KW - Minimax-rate adaptation

UR - http://www.scopus.com/inward/record.url?scp=0035397536&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0035397536&partnerID=8YFLogxK

U2 - 10.1109/18.930947

DO - 10.1109/18.930947

M3 - Article

AN - SCOPUS:0035397536

SN - 0018-9448

VL - 47

SP - 2081

EP - 2085

JO - IEEE Transactions on Information Theory

JF - IEEE Transactions on Information Theory

IS - 5

ER -

Minimax rate adaptive estimation over continuous hyper-parameters

Abstract

Keywords

Publisher link

Find It

Other files and links

Fingerprint

Cite this