CEO problem for belief sharing

Aditya Vempaty, Lav R Varshney

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

We consider the CEO problem for belief sharing. Multiple subordinates observe independently corrupted versions of uniformly distributed data and transmit coded versions over rate-limited links to a CEO who then estimates the underlying data. Agents are not allowed to convene before transmitting their observations. This formulation is motivated by the practical problem of a firm's CEO estimating uniformly distributed beliefs about a sequence of events, before acting on them. Agents' observations are modeled as jointly distributed with the underlying data through a given conditional probability density function. We study the asymptotic behavior of the minimum achievable mean squared error distortion at the CEO in the limit when the number of agents L and the sum rate R tend to infinity. We establish a 1/R2 convergence of the distortion, an intermediate regime of performance between the exponential behavior in discrete CEO problems [Berger, Zhang, and Viswanathan (1996)], and the 1/R behavior in Gaussian CEO problems [Viswanathan and Berger (1997)]. Achievability is proved by a layered architecture with scalar quantization, distributed entropy coding, and midrange estimation. The converse is proved using the Bayesian Chazan-Zakai-Ziv bound.

Original languageEnglish (US)
Title of host publication2015 IEEE Information Theory Workshop, ITW 2015
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781479955268
DOIs
StatePublished - Jun 24 2015
Event2015 IEEE Information Theory Workshop, ITW 2015 - Jerusalem, Israel
Duration: Apr 26 2015May 1 2015

Publication series

Name2015 IEEE Information Theory Workshop, ITW 2015

Other

Other2015 IEEE Information Theory Workshop, ITW 2015
CountryIsrael
CityJerusalem
Period4/26/155/1/15

Fingerprint

Probability density function
Entropy

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Networks and Communications
  • Information Systems
  • Computational Theory and Mathematics

Cite this

Vempaty, A., & Varshney, L. R. (2015). CEO problem for belief sharing. In 2015 IEEE Information Theory Workshop, ITW 2015 [7133076] (2015 IEEE Information Theory Workshop, ITW 2015). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ITW.2015.7133076

CEO problem for belief sharing. / Vempaty, Aditya; Varshney, Lav R.

2015 IEEE Information Theory Workshop, ITW 2015. Institute of Electrical and Electronics Engineers Inc., 2015. 7133076 (2015 IEEE Information Theory Workshop, ITW 2015).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Vempaty, A & Varshney, LR 2015, CEO problem for belief sharing. in 2015 IEEE Information Theory Workshop, ITW 2015., 7133076, 2015 IEEE Information Theory Workshop, ITW 2015, Institute of Electrical and Electronics Engineers Inc., 2015 IEEE Information Theory Workshop, ITW 2015, Jerusalem, Israel, 4/26/15. https://doi.org/10.1109/ITW.2015.7133076
Vempaty A, Varshney LR. CEO problem for belief sharing. In 2015 IEEE Information Theory Workshop, ITW 2015. Institute of Electrical and Electronics Engineers Inc. 2015. 7133076. (2015 IEEE Information Theory Workshop, ITW 2015). https://doi.org/10.1109/ITW.2015.7133076
Vempaty, Aditya ; Varshney, Lav R. / CEO problem for belief sharing. 2015 IEEE Information Theory Workshop, ITW 2015. Institute of Electrical and Electronics Engineers Inc., 2015. (2015 IEEE Information Theory Workshop, ITW 2015).
@inproceedings{4b9e65d7a850400086e24747a7bcd3f8,
title = "CEO problem for belief sharing",
abstract = "We consider the CEO problem for belief sharing. Multiple subordinates observe independently corrupted versions of uniformly distributed data and transmit coded versions over rate-limited links to a CEO who then estimates the underlying data. Agents are not allowed to convene before transmitting their observations. This formulation is motivated by the practical problem of a firm's CEO estimating uniformly distributed beliefs about a sequence of events, before acting on them. Agents' observations are modeled as jointly distributed with the underlying data through a given conditional probability density function. We study the asymptotic behavior of the minimum achievable mean squared error distortion at the CEO in the limit when the number of agents L and the sum rate R tend to infinity. We establish a 1/R2 convergence of the distortion, an intermediate regime of performance between the exponential behavior in discrete CEO problems [Berger, Zhang, and Viswanathan (1996)], and the 1/R behavior in Gaussian CEO problems [Viswanathan and Berger (1997)]. Achievability is proved by a layered architecture with scalar quantization, distributed entropy coding, and midrange estimation. The converse is proved using the Bayesian Chazan-Zakai-Ziv bound.",
author = "Aditya Vempaty and Varshney, {Lav R}",
year = "2015",
month = "6",
day = "24",
doi = "10.1109/ITW.2015.7133076",
language = "English (US)",
series = "2015 IEEE Information Theory Workshop, ITW 2015",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2015 IEEE Information Theory Workshop, ITW 2015",
address = "United States",

}

TY - GEN

T1 - CEO problem for belief sharing

AU - Vempaty, Aditya

AU - Varshney, Lav R

PY - 2015/6/24

Y1 - 2015/6/24

N2 - We consider the CEO problem for belief sharing. Multiple subordinates observe independently corrupted versions of uniformly distributed data and transmit coded versions over rate-limited links to a CEO who then estimates the underlying data. Agents are not allowed to convene before transmitting their observations. This formulation is motivated by the practical problem of a firm's CEO estimating uniformly distributed beliefs about a sequence of events, before acting on them. Agents' observations are modeled as jointly distributed with the underlying data through a given conditional probability density function. We study the asymptotic behavior of the minimum achievable mean squared error distortion at the CEO in the limit when the number of agents L and the sum rate R tend to infinity. We establish a 1/R2 convergence of the distortion, an intermediate regime of performance between the exponential behavior in discrete CEO problems [Berger, Zhang, and Viswanathan (1996)], and the 1/R behavior in Gaussian CEO problems [Viswanathan and Berger (1997)]. Achievability is proved by a layered architecture with scalar quantization, distributed entropy coding, and midrange estimation. The converse is proved using the Bayesian Chazan-Zakai-Ziv bound.

AB - We consider the CEO problem for belief sharing. Multiple subordinates observe independently corrupted versions of uniformly distributed data and transmit coded versions over rate-limited links to a CEO who then estimates the underlying data. Agents are not allowed to convene before transmitting their observations. This formulation is motivated by the practical problem of a firm's CEO estimating uniformly distributed beliefs about a sequence of events, before acting on them. Agents' observations are modeled as jointly distributed with the underlying data through a given conditional probability density function. We study the asymptotic behavior of the minimum achievable mean squared error distortion at the CEO in the limit when the number of agents L and the sum rate R tend to infinity. We establish a 1/R2 convergence of the distortion, an intermediate regime of performance between the exponential behavior in discrete CEO problems [Berger, Zhang, and Viswanathan (1996)], and the 1/R behavior in Gaussian CEO problems [Viswanathan and Berger (1997)]. Achievability is proved by a layered architecture with scalar quantization, distributed entropy coding, and midrange estimation. The converse is proved using the Bayesian Chazan-Zakai-Ziv bound.

UR - http://www.scopus.com/inward/record.url?scp=84938909219&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84938909219&partnerID=8YFLogxK

U2 - 10.1109/ITW.2015.7133076

DO - 10.1109/ITW.2015.7133076

M3 - Conference contribution

AN - SCOPUS:84938909219

T3 - 2015 IEEE Information Theory Workshop, ITW 2015

BT - 2015 IEEE Information Theory Workshop, ITW 2015

PB - Institute of Electrical and Electronics Engineers Inc.

ER -