On the convergence of MDL density estimation

Tong Zhang

doi:10.1007/978-3-540-27819-1_22

On the convergence of MDL density estimation

Research output: Contribution to journal › Conference article › peer-review

Abstract

We present a general information exponential inequality that measures the statistical complexity of some deterministic and randomized density estimators. Using this inequality, we are able to improve classical results concerning the convergence of two-part code MDL in [1], Moreover, we are able to derive clean finite-sample convergence bounds that are not obtainable using previous approaches.

Original language	English (US)
Pages (from-to)	315-330
Number of pages	16
Journal	Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)
Volume	3120
DOIs	https://doi.org/10.1007/978-3-540-27819-1_22
State	Published - 2004
Externally published	Yes
Event	17th Annual Conference on Learning Theory, COLT 2004 - Banff, Canada Duration: Jul 1 2004 → Jul 4 2004

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science

Online availability

10.1007/978-3-540-27819-1_22

Library availability

Discover UIUC Full Text

Cite this

@article{fe9435589edb4d489e6d43bf27407a58,

title = "On the convergence of MDL density estimation",

abstract = "We present a general information exponential inequality that measures the statistical complexity of some deterministic and randomized density estimators. Using this inequality, we are able to improve classical results concerning the convergence of two-part code MDL in [1], Moreover, we are able to derive clean finite-sample convergence bounds that are not obtainable using previous approaches.",

author = "Tong Zhang",

year = "2004",

doi = "10.1007/978-3-540-27819-1_22",

language = "English (US)",

volume = "3120",

pages = "315--330",

journal = "Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)",

issn = "0302-9743",

publisher = "Springer",

note = "17th Annual Conference on Learning Theory, COLT 2004 ; Conference date: 01-07-2004 Through 04-07-2004",

}

TY - JOUR

T1 - On the convergence of MDL density estimation

AU - Zhang, Tong

PY - 2004

Y1 - 2004

N2 - We present a general information exponential inequality that measures the statistical complexity of some deterministic and randomized density estimators. Using this inequality, we are able to improve classical results concerning the convergence of two-part code MDL in [1], Moreover, we are able to derive clean finite-sample convergence bounds that are not obtainable using previous approaches.

AB - We present a general information exponential inequality that measures the statistical complexity of some deterministic and randomized density estimators. Using this inequality, we are able to improve classical results concerning the convergence of two-part code MDL in [1], Moreover, we are able to derive clean finite-sample convergence bounds that are not obtainable using previous approaches.

UR - http://www.scopus.com/inward/record.url?scp=9444261993&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=9444261993&partnerID=8YFLogxK

U2 - 10.1007/978-3-540-27819-1_22

DO - 10.1007/978-3-540-27819-1_22

M3 - Conference article

AN - SCOPUS:9444261993

SN - 0302-9743

VL - 3120

SP - 315

EP - 330

JO - Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

JF - Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)

T2 - 17th Annual Conference on Learning Theory, COLT 2004

Y2 - 1 July 2004 through 4 July 2004

ER -

On the convergence of MDL density estimation

Abstract

ASJC Scopus subject areas

Online availability

Library availability

Related links

Fingerprint

Cite this