mlsanityData to 7 Oct 2026

The Unreasonable Effectiveness of Deep Evidential Regression

arXiv 2205.10060 ↗First posted 20 May 2022cs.LG cs.NE stat.MLcited by 40

Not on the map. Why?

Abstract (arXiv)

There is a significant need for principled uncertainty reasoning in machine learning systems as they are increasingly deployed in safety-critical domains. A new approach with uncertainty-aware regression-based neural networks (NNs), based on learning evidential distributions for aleatoric and epistemic uncertainties, shows promise over traditional deterministic methods and typical Bayesian NNs, notably with the capabilities to disentangle aleatoric and epistemic uncertainties. Despite some empirical success of Deep Evidential Regression (DER), there are important gaps in the mathematical foundation that raise the question of why the proposed technique seemingly works. We detail the theoretical shortcomings and analyze the performance on synthetic and real-world data sets, showing that Deep Evidential Regression is a heuristic rather than an exact uncertainty quantification. We go on to discuss corrections and redefinitions of how aleatoric and epistemic uncertainties should be extracted from NNs.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). Builds on 29 of its 51 references that are in the map. First posted on arXiv 20 May 2022.

Builds on

29 of 51 references.

References · 29

  1. 2017On Calibration of Modern Neural Networkscited by 4,860
  2. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  3. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  4. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  5. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  6. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  7. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  8. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  9. 2018Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNscited by 585
  10. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  11. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  12. 2015Deep Kernel Learningcited by 440
17 more
  1. 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 417
  2. 2019Deep Evidential Regressioncited by 354
  3. 2019Subspace Inference for Bayesian Deep Learningcited by 94
  4. 2022Pitfalls of Epistemic Uncertainty Quantification through Loss Minimisationcited by 65
  5. 2014Avoiding pathologies in very deep networkscited by 33
  6. 2021Deep Neural Networks as Point Estimates for Deep Gaussian Processescited by 26
  7. 2021Multivariate Deep Evidential Regressioncited by 23
  8. 2021Efficient and Robust LiDAR-Based End-to-End Navigationcited by 22
  9. 2021Vision-Based Autonomous Car Racing Using Deep Imitative Reinforcement Learningcited by 21
  10. 2021Robust Monocular Localization in Sparse HD Maps Leveraging Multi-Task Uncertainty Estimationcited by 11
  11. 2019Towards calibrated and scalable uncertainty representations for neural networkscited by 10
  12. 2018Classifier-agnostic saliency map extractioncited by 7
  13. 2018Gradient conjugate priors and multi-layer neural networkscited by 6
  14. 2019A Parsimonious Tour of Bayesian Model Uncertaintycited by 5
  15. 2020Neuro-symbolic Neurodegenerative Disease Modeling as Probabilistic Programmed Deep Kernelscited by 5
  16. 2021Performance of a GPU- and Time-Efficient Pseudo 3D Network for Magnetic Resonance Image Super-Resolution and Motion Artifact Reductioncited by 4
  17. 2018Sampling-based Bayesian Inference with gradient uncertaintycited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 7; 2024: 11; 2025: 10; 2026: 12.

40 papers.

Sort:

By area:

  1. 2023Uncertainty Estimation by Fisher Information-based Evidential Deep Learningcited by 58
  2. 2023On Second-Order Scoring Rules for Epistemic Uncertainty Quantificationcited by 38
  3. 2023Second-Order Uncertainty Quantification: A Distance-Based Approachcited by 35
  4. 2024Is Epistemic Uncertainty Faithfully Represented by Evidential Deep Learning Methods?cited by 34
  5. 2024A Comprehensive Survey on Evidential Deep Learning and Its Applicationscited by 25
  6. 2024Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?cited by 17
  7. 2024Revisiting Essential and Nonessential Settings of Evidential Deep Learningcited by 15
  8. 2023Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applicationscited by 11
  9. 2024Beyond Uncertainty: Evidential Deep Learning for Robust Video Temporal Groundingcited by 10
  10. 2025Position: Epistemic uncertainty estimation methods are fundamentally incompletecited by 8
  11. 2025A calibration test for evaluating set-based epistemic uncertainty representationscited by 7
  12. 2025These Magic Moments: Differentiable Uncertainty Quantification of Radiance Field Modelscited by 6
28 more
  1. 2023Deep Evidential Learning for Bayesian Quantile Regressioncited by 5
  2. 2025Reducing Aleatoric and Epistemic Uncertainty through Multi-modal Data Acquisitioncited by 5
  3. 2024Outlier-Detection for Reactive Machine Learned Potential Energy Surfacescited by 4
  4. 2024Uncertainty-Guided Self-Questioning and Answering for Video-Language Alignmentcited by 4
  5. 2026Uncertainty in Physics and AI: Taxonomy, Quantification, and Validationcited by 3
  6. 2026ELVAE: Evidential Learning-Based Variational Autoencoder for Uncertainty-Aware Generationcited by 3
  7. 2024Uncertainty Aware Tropical Cyclone Wind Speed Estimation from Satellite Datacited by 2
  8. 2024Neural Network Prediction of Strong Lensing Systems with Domain Adaptation and Uncertainty Quantificationcited by 2
  9. 2024DeepUQ: Assessing the Aleatoric Uncertainties from two Deep Learning Methodscited by 2
  10. 2025Overcoming Non-stationary Dynamics with Evidential Proximal Policy Optimizationcited by 2
  11. 2025PRESCRIBE: Predicting Single-Cell Responses with Bayesian Estimationcited by 2
  12. 2023Human-in-the-loop: Towards Label Embeddings for Measuring Classification Difficultycited by 1
  13. 2025CARE: Confidence-Aware Regression Estimation of building density fine-tuning EO Foundation Modelscited by 1
  14. 2025On Uncertainty Calibration for Equivariant Functionscited by 1
  15. 2026A Ground-Truth Framework for Uncertainty Disentanglement with Posterior Riskcited by 1
  16. 2026PEEL: Physics-Enabled Evidential Learning for Identifiable Uncertainty in CT Imagingcited by 1
  17. 2023Probabilistic MIMO U-Net: Efficient and Accurate Uncertainty Estimation for Pixel-wise Regressioncited by 0
  18. 2024Multivariate Bayesian Last Layer for Regression with Uncertainty Quantification and Decompositioncited by 0
  19. 2025CONTINA: Confidence Interval for Traffic Demand Prediction with Coverage Guaranteecited by 0
  20. 2025Principled Input-Output-Conditioned Post-Hoc Uncertainty Estimation for Regression Networkscited by 0
  21. 2026EviNAM: Intelligibility and Uncertainty via Evidential Neural Additive Modelscited by 0
  22. 2026Uncertainty Quantification in Federated Granger Causality Learningcited by 0
  23. 2026TerraNova: A Foundation Model for the Anthropocenecited by 0
  24. 2026ELECTRIC: Evidential Learning-Enhanced CT Reconstruction via Iterative Correctioncited by 0
  25. 2026Deep Evidential Regression for Sparse Forest Height Estimation from Multimodal Satellite Imagerycited by 0
  26. 2026Uncertainty-Driven Replay Memory for Reinforcement Learningcited by 0
  27. 2026Theoretical Study on the Evidential Learning-based Variational Autoencodercited by 0
  28. 2026PEEL-DDPM: Physics-Enabled Evidential Learning for the Denoising Diffusion Probabilistic Modelcited by 0