# Generalized Regularized Evidential Deep Learning Models: Theory and Comprehensive Evaluation Source: [Generalized Regularized Evidential Deep Learning Models: Theory and Comprehensive Evaluation]() Collection index: [llms.txt]() Data updated: 2026-01-02T05:00:04.167Z Authors: Deep Shankar Pandey, Hyomin Choi, Qi Yu Published: 2025-12-27T11:26:18.000Z ## Abstract Evidential deep learning (EDL) models, based on Subjective Logic, introduce a principled and computationally efficient way to make deterministic neural networks uncertainty-aware. The resulting evidential models can quantify fine-grained uncertainty using learned evidence. However, the Subjective-Logic framework constrains evidence to be non-negative, requiring specific activation functions whose geometric properties can induce activation-dependent learning-freeze behavior: a regime where gradients become extremely small for samples mapped into low-evidence regions. We theoretically characterize this behavior and analyze how different evidential activations influence learning dynamics. Building on this analysis, we design a general family of activation functions and corresponding evidential regularizers that provide an alternative pathway for consistent evidence updates across activation regimes. Extensive experiments on four benchmark classification problems (MNIST, CIFAR-10, CIFAR-100, and Tiny-ImageNet), two few-shot classification problems, and blind face restoration problem empirically validate the developed theory and demonstrate the effectiveness of the proposed generalized regularized evidential models. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Blind Face Restoration on CelebA](): Blind Face Restoration; CelebA; PSNR: 22.33. ## Original sources and implementation [Original paper]() [PDF]()