Same-Decision Probability: threshold robustness and application to explanation

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

Abstract

The same-decision probability (SDP) is a confidence measure for threshold-based decisions. In this paper we detail various properties of the SDP that allow for studying its robustness to changes in the threshold value upon which a decision is based. In addition to expressing confidence in a decision, the SDP has proven to be a useful tool in other contexts, such as that of information gathering. We demonstrate that the properties of the SDP as established in this paper allow for its application in the context of explaining Bayesian network classifiers as well.
Original languageEnglish
Title of host publicationProceedings of the Ninth International Conference on Probabilistic Graphical Models (PGM)
EditorsVáclav Kratochvíl, Milan Studený
Pages368-379
Publication statusPublished - Sept 2018
EventNinth International Conference on Probabilistic Graphical Models (PGM) - Prague, Czech Republic
Duration: 11 Sept 201814 Sept 2018
Conference number: 9

Publication series

NameProceedings of Machine Learning Research
PublisherPMLR
Volume72

Conference

ConferenceNinth International Conference on Probabilistic Graphical Models (PGM)
Abbreviated titlePGM
Country/TerritoryCzech Republic
CityPrague
Period11/09/1814/09/18

Keywords

  • Bayesian network classifiers
  • threshold-based decisions
  • Same-decision probability
  • robustness
  • explanations

Fingerprint

Dive into the research topics of 'Same-Decision Probability: threshold robustness and application to explanation'. Together they form a unique fingerprint.

Cite this