| Jun Bao and Arno Onken |
| Tue 20 Nov 2018, 11:00 - 12:00 |
| IF 4.31/4.33 |
If you have a question about this talk, please contact: Gareth Beedham (gbeedham)
Arno Onken
Title: Non-parametric copula-based information estimation
Abstract:
Estimation of mutual information has become indispensable in many fields but is complicated by its dependence on the characteristics of the underlying probability distributions. Here we propose a non-parametric copula-based information estimator which exploits a close relationship between the copula framework and mutual information. The resulting estimator is applicable to both continuous and discrete variables. We validate our method on artificial samples drawn from various statistical distributions and show that our estimator compares favourably with alternative estimators in a wide range of situations. In particular, we show that our estimator strikes a good balance between general applicability to various dependence structures and the number of samples required for robust information estimates.