General Uncertainty Estimation with Delta Variances

ArXi:2502.14698v2 Announce Type: replace-cross Decision makers may suffer from uncertainty induced by limited data. This may be mitigated by accounting for epistemic uncertainty, which is however challenging to estimate efficiently for large neural networks. To this extent we investigate Delta Variances, a family of algorithms for epistemic uncertainty quantification, that is computationally efficient and convenient to implement. It can be applied to neural networks and general functions composed of neural networks.