Projects per year
For nonlinear supervised learning models, assessing the importance of predictor variables or their interactions is not straightforward because importance can vary in the domain of the variables. Importance can be assessed locally with sensitivity analysis using general methods that rely on the model's predictions or their derivatives. In this work, we extend derivative based sensitivity analysis to a Bayesian setting by differentiating the Rényi divergence of a model's predictive distribution. By utilising the predictive distribution instead of a point prediction, the model uncertainty is taken into account in a principled way. Our empirical results on simulated and real data sets demonstrate accurate and reliable identification of important variables and interaction effects compared to alternative methods.
|Title of host publication||Proceedings of the Thirty-Seventh Conference on Uncertainty in Artificial Intelligence|
|Publication status||Published - 12 Dec 2021|
|MoE publication type||A4 Article in a conference publication|
|Event||Conference on Uncertainty in Artificial Intelligence - Virtual, Online|
Duration: 27 Jul 2021 → 29 Jul 2021
|Name||Proceedings of Machine Learning Research|
|Conference||Conference on Uncertainty in Artificial Intelligence|
|Period||27/07/2021 → 29/07/2021|
FingerprintDive into the research topics of 'Uncertainty-aware Sensitivity Analysis Using Rényi Divergences'. Together they form a unique fingerprint.
- 1 Finished
FCAI: Finnish Center for Artificial Intelligence (FCAI)
Vehtari, A. & Yamin, A.
01/01/2019 → 31/12/2022
Project: Academy of Finland: Other research funding