Performance Guarantees for Information Theoretic Active Inference

Jason L. Williams, John W. Fisher III, Alan S. Willsky
Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics, PMLR 2:620-627, 2007.

Abstract

In many estimation problems, the measurement process can be actively controlled to alter the information received. The control choices made in turn determine the performance that is possible in the underlying inference task. In this paper, we discuss performance guarantees for heuristic algorithms for adaptive measurement selection in sequential estimation problems, where the inference criterion is mutual information. We also demonstrate the performance of our tighter online computable performance guarantees through computational simulations.

Cite this Paper

BibTeX
@InProceedings{pmlr-v2-williams07a, title = {Performance Guarantees for Information Theoretic Active Inference}, author = {Williams, Jason L. and III, John W. Fisher and Willsky, Alan S.}, booktitle = {Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics}, pages = {620--627}, year = {2007}, editor = {Meila, Marina and Shen, Xiaotong}, volume = {2}, series = {Proceedings of Machine Learning Research}, address = {San Juan, Puerto Rico}, month = {21--24 Mar}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v2/williams07a/williams07a.pdf}, url = {https://proceedings.mlr.press/v2/williams07a.html}, abstract = {In many estimation problems, the measurement process can be actively controlled to alter the information received. The control choices made in turn determine the performance that is possible in the underlying inference task. In this paper, we discuss performance guarantees for heuristic algorithms for adaptive measurement selection in sequential estimation problems, where the inference criterion is mutual information. We also demonstrate the performance of our tighter online computable performance guarantees through computational simulations.} }
Endnote
%0 Conference Paper %T Performance Guarantees for Information Theoretic Active Inference %A Jason L. Williams %A John W. Fisher III %A Alan S. Willsky %B Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2007 %E Marina Meila %E Xiaotong Shen %F pmlr-v2-williams07a %I PMLR %P 620--627 %U https://proceedings.mlr.press/v2/williams07a.html %V 2 %X In many estimation problems, the measurement process can be actively controlled to alter the information received. The control choices made in turn determine the performance that is possible in the underlying inference task. In this paper, we discuss performance guarantees for heuristic algorithms for adaptive measurement selection in sequential estimation problems, where the inference criterion is mutual information. We also demonstrate the performance of our tighter online computable performance guarantees through computational simulations.
RIS
TY - CPAPER TI - Performance Guarantees for Information Theoretic Active Inference AU - Jason L. Williams AU - John W. Fisher III AU - Alan S. Willsky BT - Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics DA - 2007/03/11 ED - Marina Meila ED - Xiaotong Shen ID - pmlr-v2-williams07a PB - PMLR DP - Proceedings of Machine Learning Research VL - 2 SP - 620 EP - 627 L1 - http://proceedings.mlr.press/v2/williams07a/williams07a.pdf UR - https://proceedings.mlr.press/v2/williams07a.html AB - In many estimation problems, the measurement process can be actively controlled to alter the information received. The control choices made in turn determine the performance that is possible in the underlying inference task. In this paper, we discuss performance guarantees for heuristic algorithms for adaptive measurement selection in sequential estimation problems, where the inference criterion is mutual information. We also demonstrate the performance of our tighter online computable performance guarantees through computational simulations. ER -
APA
Williams, J.L., III, J.W.F. & Willsky, A.S.. (2007). Performance Guarantees for Information Theoretic Active Inference. Proceedings of the Eleventh International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 2:620-627 Available from https://proceedings.mlr.press/v2/williams07a.html.

Related Material