Uncertainty Quantification Metrics for Deep Regression

arXiv:2405.04278v1 Announce Type: new
Abstract: When deploying deep neural networks on robots or other physical systems, the learned model should reliably quantify predictive uncertainty. A reliable uncertainty allows downstream modules to reason about the safety of its actions. In this work, we address metrics for evaluating such an uncertainty. Specifically, we focus on regression tasks, and investigate Area Under Sparsification Error (AUSE), Calibration Error, Spearman's Rank Correlation, and Negative Log-Likelihood (NLL). Using synthetic regression datasets, we look into how those …

abstract arxiv cs.lg cs.ro focus metrics modules networks neural networks predictive quantification reason regression robots safety systems type uncertainty work