Plug-in Losses for Evidential Deep Learning: A Simplified Framework for Uncertainty Estimation that Includes the Softmax Classifier

• URL: http://arxiv.org/abs/2605.22746v1
• Date: Thu, 21 May 2026 17:15:10 GMT
• Title: Plug-in Losses for Evidential Deep Learning: A Simplified Framework for Uncertainty Estimation that Includes the Softmax Classifier
• Abstract summary: Real-world sensor-based learning systems require uncertainty estimation that is both reliable and computationally efficient.<n>Evidential Deep Learning (EDL) provides single-pass uncertainty estimation by modeling the class probabilities via Dirichlet distributions.<n>We address this issue by approximating the objective of the first-order empirical risk minimization problem induced by EDL with a plug-in loss evaluated at the Dirichlet mean.<n>We validate the proposed simplified objectives on the Google Speech Commands dataset and show that they achieve predictive accuracy and selective prediction performance comparable to classical EDL.
• Score: 3.6423651166048874
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Real-world sensor-based learning systems require uncertainty estimation that is both reliable and computationally efficient. Evidential Deep Learning (EDL) provides single-pass uncertainty estimation by modeling the class probabilities via Dirichlet distributions, where the Dirichlet parameters are predicted by a learned neural network mapping. However, this approach can lead to computational challenges, as Dirichlet expected objectives are more complex than standard supervised learning losses, complicating their analysis and implementation. We address this issue by approximating the objective of the first-order empirical risk minimization problem induced by EDL with a plug-in loss evaluated at the Dirichlet mean and show that, under mild assumptions, the approximation error decays with growing evidence for a broad class of loss functions, including mean-squared error and cross-entropy loss. As a special case, our analysis provides justification for the use of softmax in the context of uncertainty estimation, since under a particular evidence-to-Dirichlet mapping, our framework includes the standard softmax classifier. We validate the proposed simplified objectives on the Google Speech Commands dataset and show that they achieve predictive accuracy and selective prediction performance comparable to classical EDL, while being simpler to implement using standard deep learning losses and training pipelines. To the best of our knowledge, this empirical analysis is the first to obtain coverage-accuracy trade-offs for speech recognition tasks through EDL.

Related papers

• A Perception vs. Distortion Perspective on Score-Based Generative Channel Estimation [2.378977673869692]
  We present a theoretically grounded interpretation of score-based channel estimation.<n>We quantify the excess risk incurred by standard distortion-minimization approaches.<n>Under high predictive uncertainty, the large excess risk gap can be offset by score-based estimation.
  arXiv  Detail & Related papers  (2026-06-15T15:00:24Z)
• Variational Inference for Evidential Deep Learning [69.9353638875714]
  We propose a mathematically principled framework, Variational Inference Evidential Deep Learning (VI-EDL)<n>VI-EDL achieves state-of-the-art performance in out-of-distribution detection, noise detection and autonomous driving scenario.
  arXiv  Detail & Related papers  (2026-05-26T02:32:59Z)
• Possibilistic Predictive Uncertainty for Deep Learning [75.00607359322863]
  We introduce Dirichlet-approximated possibilistic posterior predictions (DAPPr)<n>DAPPr is a principled framework leveraging possibility theory.<n>This projection-and-approximation strategy yields a simple training objective with closed-form solutions.
  arXiv  Detail & Related papers  (2026-05-01T12:14:01Z)
• Ensemble-Based Dirichlet Modeling for Predictive Uncertainty and Selective Classification [1.77898701462905]
  Evidential Deep Learning aims to address limitations by producing uncertainty estimates in a single pass.<n>This work introduces an alternative Dirichlet parameter estimation strategy by applying a method of moments estimator to ensembles of softmax outputs.<n>We show that the improved stability and predictive uncertainty behavior of these ensemble-derived Dirichlet estimates translate into stronger performance in downstream uncertainty-guided applications.
  arXiv  Detail & Related papers  (2026-04-07T16:28:20Z)
• Principled Input-Output-Conditioned Post-Hoc Uncertainty Estimation for Regression Networks [1.4671424999873808]
  Uncertainty is critical in safety-sensitive applications but is often omitted from off-the-shelf neural networks due to adverse effects on predictive performance.<n>We propose a theoretically grounded framework for post-hoc uncertainty estimation in regression tasks by fitting an auxiliary model to both original inputs and frozen model outputs.
  arXiv  Detail & Related papers  (2025-06-01T09:13:27Z)
• PredictaBoard: Benchmarking LLM Score Predictability [50.47497036981544]
  Large Language Models (LLMs) often fail unpredictably.<n>This poses a significant challenge to ensuring their safe deployment.<n>We present PredictaBoard, a novel collaborative benchmarking framework.
  arXiv  Detail & Related papers  (2025-02-20T10:52:38Z)
• Revisiting Essential and Nonessential Settings of Evidential Deep Learning [70.82728812001807]
  Evidential Deep Learning (EDL) is an emerging method for uncertainty estimation. We propose Re-EDL, a simplified yet more effective variant of EDL.
  arXiv  Detail & Related papers  (2024-10-01T04:27:07Z)
• Probability Distribution Learning and Its Application in Deep Learning [0.0]
  This paper introduces a novel theoretical learning framework, termed probability distribution learning (PD learning)<n>PD learning focuses on learning the underlying probability distribution, which is modeled as a random variable within the probability simplex.
  arXiv  Detail & Related papers  (2024-06-09T06:49:22Z)
• Querying Easily Flip-flopped Samples for Deep Active Learning [63.62397322172216]
  Active learning is a machine learning paradigm that aims to improve the performance of a model by strategically selecting and querying unlabeled data. One effective selection strategy is to base it on the model's predictive uncertainty, which can be interpreted as a measure of how informative a sample is. This paper proposes the it least disagree metric (LDM) as the smallest probability of disagreement of the predicted label.
  arXiv  Detail & Related papers  (2024-01-18T08:12:23Z)
• Uncertainty Estimation by Fisher Information-based Evidential Deep Learning [61.94125052118442]
  Uncertainty estimation is a key factor that makes deep learning reliable in practical applications. We propose a novel method, Fisher Information-based Evidential Deep Learning ($mathcalI$-EDL) In particular, we introduce Fisher Information Matrix (FIM) to measure the informativeness of evidence carried by each sample, according to which we can dynamically reweight the objective loss terms to make the network more focused on the representation learning of uncertain classes.
  arXiv  Detail & Related papers  (2023-03-03T16:12:59Z)
• A Learning-Based Optimal Uncertainty Quantification Method and Its Application to Ballistic Impact Problems [1.713291434132985]
  This paper concerns the optimal (supremum and infimum) uncertainty bounds for systems where the input (or prior) measure is only partially/imperfectly known. We demonstrate the learning based framework on the uncertainty optimization problem. We show that the approach can be used to construct maps for the performance certificate and safety in engineering practice.
  arXiv  Detail & Related papers  (2022-12-28T14:30:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.