Maximum entropy identification and min-max optimal prediction

Craig Shankwitz; Tryphon T. Georgiou

Maximum entropy identification and min-max optimal prediction

Craig Shankwitz, Tryphon T. Georgiou

Electrical and Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

The authors consider the problem of worst case prediction of stationary discrete time stochastic processes. For certain classes of models and predictor, there is a uniformly optimal solution to the prediction problem. This solution is unique, and the uniform optimality is related to the principle of maximum entropy. An example is provided for which the min-max solution is not equal to the max-min solution.

Original language	English (US)
Title of host publication	Proceedings of the IEEE Conference on Decision and Control
Publisher	Publ by IEEE
Pages	617-622
Number of pages	6
ISBN (Print)	0780304500
State	Published - Jan 1 1992
Event	Proceedings of the 30th IEEE Conference on Decision and Control Part 1 (of 3) - Brighton, Engl Duration: Dec 11 1991 → Dec 13 1991

Other

Other	Proceedings of the 30th IEEE Conference on Decision and Control Part 1 (of 3)
City	Brighton, Engl
Period	12/11/91 → 12/13/91

Find It

Find It at U of M Libraries

Cite this

@inproceedings{80fbb6441dbb4a789d9217d32fd859f9,

title = "Maximum entropy identification and min-max optimal prediction",

abstract = "The authors consider the problem of worst case prediction of stationary discrete time stochastic processes. For certain classes of models and predictor, there is a uniformly optimal solution to the prediction problem. This solution is unique, and the uniform optimality is related to the principle of maximum entropy. An example is provided for which the min-max solution is not equal to the max-min solution.",

author = "Craig Shankwitz and Georgiou, {Tryphon T.}",

year = "1992",

month = jan,

day = "1",

language = "English (US)",

isbn = "0780304500",

pages = "617--622",

booktitle = "Proceedings of the IEEE Conference on Decision and Control",

publisher = "Publ by IEEE",

note = "Proceedings of the 30th IEEE Conference on Decision and Control Part 1 (of 3) ; Conference date: 11-12-1991 Through 13-12-1991",

}

TY - GEN

T1 - Maximum entropy identification and min-max optimal prediction

AU - Shankwitz, Craig

AU - Georgiou, Tryphon T.

PY - 1992/1/1

Y1 - 1992/1/1

N2 - The authors consider the problem of worst case prediction of stationary discrete time stochastic processes. For certain classes of models and predictor, there is a uniformly optimal solution to the prediction problem. This solution is unique, and the uniform optimality is related to the principle of maximum entropy. An example is provided for which the min-max solution is not equal to the max-min solution.

AB - The authors consider the problem of worst case prediction of stationary discrete time stochastic processes. For certain classes of models and predictor, there is a uniformly optimal solution to the prediction problem. This solution is unique, and the uniform optimality is related to the principle of maximum entropy. An example is provided for which the min-max solution is not equal to the max-min solution.

UR - http://www.scopus.com/inward/record.url?scp=0026618418&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026618418&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026618418

SN - 0780304500

SP - 617

EP - 622

BT - Proceedings of the IEEE Conference on Decision and Control

PB - Publ by IEEE

T2 - Proceedings of the 30th IEEE Conference on Decision and Control Part 1 (of 3)

Y2 - 11 December 1991 through 13 December 1991

ER -

Maximum entropy identification and min-max optimal prediction

Abstract

Other

Find It

Other files and links

Fingerprint

Cite this