Review for NeurIPS paper: Improving model calibration with accuracy versus uncertainty optimization

Additional Feedback: Post Rebuttal: The authors have satisfactorily addressed all my concerns. Specifically, my major concern on the absence of theoretical justification behind this approach will be addressed by authors incorporating R4's suggestion on discussing how the approach serves as loss-calibrated inference method. This would certainly make this paper strong. In this paper, the authors propose a modified loss function for improving the performance of uncertainty-aware DNNs. They show applicability of their loss with mean-field stochastic variational inference (SVI) based BNN.