Three new sensitivity analysis methods for influence diagrams

Debarun Bhattacharjya, Ross Shachter
Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, PMLR R8:56-64, 2010.

Abstract

Performing sensitivity analysis for influence diagrams using the decision circuit frame- work is particularly convenient, since the partial derivatives with respect to every pa- rameter are readily available [Bhattacharjya and Shachter, 2007; 2008]. In this paper we present three non-linear sensitivity anal- ysis methods that utilize this partial deriva- tive information and therefore do not require re-evaluating the decision situation multiple times. Specifically, we show how to efficiently compare strategies in decision situations, per- form sensitivity to risk aversion and compute the value of perfect hedging [Seyller, 2008].

Cite this Paper

BibTeX
@InProceedings{pmlr-vR8-bhattacharjya10a, title = {Three new sensitivity analysis methods for influence diagrams}, author = {Bhattacharjya, Debarun and Shachter, Ross}, booktitle = {Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence}, pages = {56--64}, year = {2010}, editor = {Grünwald, Peter and Spirtes, Peter}, volume = {R8}, series = {Proceedings of Machine Learning Research}, month = {08--11 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r8/main/assets/bhattacharjya10a/bhattacharjya10a.pdf}, url = {https://proceedings.mlr.press/r8/bhattacharjya10a.html}, abstract = {Performing sensitivity analysis for influence diagrams using the decision circuit frame- work is particularly convenient, since the partial derivatives with respect to every pa- rameter are readily available [Bhattacharjya and Shachter, 2007; 2008]. In this paper we present three non-linear sensitivity anal- ysis methods that utilize this partial deriva- tive information and therefore do not require re-evaluating the decision situation multiple times. Specifically, we show how to efficiently compare strategies in decision situations, per- form sensitivity to risk aversion and compute the value of perfect hedging [Seyller, 2008].}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Three new sensitivity analysis methods for influence diagrams %A Debarun Bhattacharjya %A Ross Shachter %B Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2010 %E Peter Grünwald %E Peter Spirtes %F pmlr-vR8-bhattacharjya10a %I PMLR %P 56--64 %U https://proceedings.mlr.press/r8/bhattacharjya10a.html %V R8 %X Performing sensitivity analysis for influence diagrams using the decision circuit frame- work is particularly convenient, since the partial derivatives with respect to every pa- rameter are readily available [Bhattacharjya and Shachter, 2007; 2008]. In this paper we present three non-linear sensitivity anal- ysis methods that utilize this partial deriva- tive information and therefore do not require re-evaluating the decision situation multiple times. Specifically, we show how to efficiently compare strategies in decision situations, per- form sensitivity to risk aversion and compute the value of perfect hedging [Seyller, 2008]. %Z Reissued by PMLR on 04 October 2026.
APA
Bhattacharjya, D. & Shachter, R.. (2010). Three new sensitivity analysis methods for influence diagrams. Proceedings of the 26th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R8:56-64 Available from https://proceedings.mlr.press/r8/bhattacharjya10a.html. Reissued by PMLR on 04 October 2026.

Related Material