Abstract
In the context of evidence evaluation, where the probability of evidence given a certain hypothesis is
considered, different pieces of evidence are often combined in a naive way by assuming conditional
independence. In this paper we present a number of results that can be used to assess both the
importance of a reliable likelihood-ratio estimate and the impact of neglecting dependencies among
pieces of evidence for the purpose of evidence evaluation. We analytically study the effect of
changes in dependencies between pieces of evidence on the likelihood ratio, and provide both
theoretical and empirical bounds on the error in likelihood occasioned by assuming independences
that do not hold in practice. In addition, a simple measure of influence strength between pieces of
evidence is proposed.
considered, different pieces of evidence are often combined in a naive way by assuming conditional
independence. In this paper we present a number of results that can be used to assess both the
importance of a reliable likelihood-ratio estimate and the impact of neglecting dependencies among
pieces of evidence for the purpose of evidence evaluation. We analytically study the effect of
changes in dependencies between pieces of evidence on the likelihood ratio, and provide both
theoretical and empirical bounds on the error in likelihood occasioned by assuming independences
that do not hold in practice. In addition, a simple measure of influence strength between pieces of
evidence is proposed.
| Original language | English |
|---|---|
| Title of host publication | Conference on Probabilistic Graphical Models, 6-9 September 2016, Lugano, Switzerland |
| Editors | Alessandro Antonucci, Giorgio Corani, Cassio Polpo Campos |
| Publisher | MLResearchPress |
| Pages | 426-473 |
| Publication status | Published - 2016 |
| Event | International Conference on Probabilistic Graphical Models - Lugano, Switzerland Duration: 6 Sept 2016 → 9 Sept 2016 |
Publication series
| Name | Journal of Machine Learning Research Workshop and Conference Proceedings |
|---|---|
| Publisher | MLResearchPress |
| Volume | 52 |
Conference
| Conference | International Conference on Probabilistic Graphical Models |
|---|---|
| Abbreviated title | PGM |
| Country/Territory | Switzerland |
| City | Lugano |
| Period | 6/09/16 → 9/09/16 |
Keywords
- Evidence evaluation
- independence violations
- error in overall likelihood
- influence measures