Maximum entropy identification and min-max optimal prediction

Craig Shankwitz, Tryphon T. Georgiou

Research output: Chapter in Book/Report/Conference proceedingConference 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 languageEnglish (US)
Title of host publicationProceedings of the IEEE Conference on Decision and Control
PublisherPubl by IEEE
Pages617-622
Number of pages6
ISBN (Print)0780304500
StatePublished - Jan 1 1992
EventProceedings of the 30th IEEE Conference on Decision and Control Part 1 (of 3) - Brighton, Engl
Duration: Dec 11 1991Dec 13 1991

Other

OtherProceedings of the 30th IEEE Conference on Decision and Control Part 1 (of 3)
CityBrighton, Engl
Period12/11/9112/13/91

Fingerprint Dive into the research topics of 'Maximum entropy identification and min-max optimal prediction'. Together they form a unique fingerprint.

Cite this