Convergence of best phi -entropy estimates

M. Teboulle; I. Vajda

doi:10.1109/18.179378

Convergence of best phi -entropy estimates

M. Teboulle, I. Vajda

School of Mathematical Sciences

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

26 Scopus citations

Abstract

Minimization problems involving phi -entropy functionals (a generalization of Boltzmann-Shannon entropy) are studied over a given set A and a sequence of sets A/sub n/ and the properties of their optimal solutions x/sub phi /, x/sub n/. Under certain conditions on the objective functional and the sets A and A/sub n/, it is proven that as n increases to infinity, the optimal solution x/sub n/ converges in L/sub 1/ norm to the test phi -entropy estimate x/sub phi /.

Original language	Undefined/Unknown
Pages (from-to)	297-301
Number of pages	5
Journal	IEEE Transactions on Information Theory
Volume	39
Issue number	1
DOIs	https://doi.org/10.1109/18.179378
State	Published - 1 Jan 1993

Keywords

Entropy functionals
convex optimization
maximum entropy methods
norm convergence
set-convergence

Access to Document

10.1109/18.179378

Cite this

@article{8495f284a44f447fa15a7a663474e7b9,

title = "Convergence of best phi -entropy estimates",

abstract = "Minimization problems involving phi -entropy functionals (a generalization of Boltzmann-Shannon entropy) are studied over a given set A and a sequence of sets A/sub n/ and the properties of their optimal solutions x/sub phi /, x/sub n/. Under certain conditions on the objective functional and the sets A and A/sub n/, it is proven that as n increases to infinity, the optimal solution x/sub n/ converges in L/sub 1/ norm to the test phi -entropy estimate x/sub phi /.",

keywords = "Entropy functionals, convex optimization, maximum entropy methods, norm convergence, set-convergence",

author = "M. Teboulle and I. Vajda",

year = "1993",

month = jan,

day = "1",

doi = "10.1109/18.179378",

language = "???core.languages.und???",

volume = "39",

pages = "297--301",

journal = "IEEE Transactions on Information Theory",

issn = "1557-9654",

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

number = "1",

}

TY - JOUR

T1 - Convergence of best phi -entropy estimates

AU - Teboulle, M.

AU - Vajda, I.

PY - 1993/1/1

Y1 - 1993/1/1

N2 - Minimization problems involving phi -entropy functionals (a generalization of Boltzmann-Shannon entropy) are studied over a given set A and a sequence of sets A/sub n/ and the properties of their optimal solutions x/sub phi /, x/sub n/. Under certain conditions on the objective functional and the sets A and A/sub n/, it is proven that as n increases to infinity, the optimal solution x/sub n/ converges in L/sub 1/ norm to the test phi -entropy estimate x/sub phi /.

AB - Minimization problems involving phi -entropy functionals (a generalization of Boltzmann-Shannon entropy) are studied over a given set A and a sequence of sets A/sub n/ and the properties of their optimal solutions x/sub phi /, x/sub n/. Under certain conditions on the objective functional and the sets A and A/sub n/, it is proven that as n increases to infinity, the optimal solution x/sub n/ converges in L/sub 1/ norm to the test phi -entropy estimate x/sub phi /.

KW - Entropy functionals

KW - convex optimization

KW - maximum entropy methods

KW - norm convergence

KW - set-convergence

UR - http://www.scopus.com/inward/record.url?scp=0027283206&partnerID=8YFLogxK

U2 - 10.1109/18.179378

DO - 10.1109/18.179378

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

SN - 1557-9654

VL - 39

SP - 297

EP - 301

JO - IEEE Transactions on Information Theory

JF - IEEE Transactions on Information Theory

IS - 1

ER -

Convergence of best phi -entropy estimates

Abstract

Keywords

Access to Document

Other files and links

Cite this