mlsanityData to 7 Oct 2026

Multivariate Deep Evidential Regression

arXiv 2104.06135 ↗First posted 13 Apr 2021cs.LG cs.NE stat.MLcited by 23

Not on the map. Why?

Abstract (arXiv)

There is 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 neural networks (NNs), based on learning evidential distributions for aleatoric and epistemic uncertainties, shows promise over traditional deterministic methods and typical Bayesian NNs, yet several important gaps in the theory and implementation of these networks remain. We discuss three issues with a proposed solution to extract aleatoric and epistemic uncertainties from regression-based neural networks. The approach derives a technique by placing evidential priors over the original Gaussian likelihood function and training the NN to infer the hyperparameters of the evidential distribution. Doing so allows for the simultaneous extraction of both uncertainties without sampling or utilization of out-of-distribution data for univariate regression tasks. We describe the outstanding issues in detail, provide a possible solution, and generalize the deep evidential regression technique for multivariate cases.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 22 of its 34 references that are in the map. First posted on arXiv 13 Apr 2021.

Builds on

22 of 34 references.

References · 22

  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. 2016End to End Learning for Self-Driving Carscited by 1,000
  7. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
  8. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  9. 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
  10. 2018Loss Surfaces, Mode Connectivity, and Fast Ensembling of DNNscited by 585
  11. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  12. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
10 more
  1. 2015Deep Kernel Learningcited by 440
  2. 2019Deep Evidential Regressioncited by 354
  3. 2021DEUP: Direct Epistemic Uncertainty Predictioncited by 102
  4. 2019Subspace Inference for Bayesian Deep Learningcited by 94
  5. 2014Avoiding pathologies in very deep networkscited by 33
  6. 2019Towards calibrated and scalable uncertainty representations for neural networkscited by 10
  7. 2018Gradient conjugate priors and multi-layer neural networkscited by 6
  8. 2019A Parsimonious Tour of Bayesian Model Uncertaintycited by 5
  9. 2020Neuro-symbolic Neurodegenerative Disease Modeling as Probabilistic Programmed Deep Kernelscited by 5
  10. 2018Sampling-based Bayesian Inference with gradient uncertaintycited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 4; 2024: 7; 2025: 3; 2026: 5.

23 papers.

Sort:

  1. 2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
  2. 2022The Unreasonable Effectiveness of Deep Evidential Regressioncited by 40
  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. 2024Revisiting Essential and Nonessential Settings of Evidential Deep Learningcited by 15
  7. 2024Uncertainty Regularized Evidential Regressioncited by 13
  8. 2023Evidential Deep Learning: Enhancing Predictive Uncertainty Estimation for Earth System Science Applicationscited by 11
  9. 2023Deep Evidential Learning for Bayesian Quantile Regressioncited by 5
  10. 2026Scaling laws for amplitude surrogatescited by 5
  11. 2021Uncertainty Quantification in Neural Differential Equationscited by 3
  12. 2026Uncertainty in Physics and AI: Taxonomy, Quantification, and Validationcited by 3
11 more
  1. 2024Neural Network Prediction of Strong Lensing Systems with Domain Adaptation and Uncertainty Quantificationcited by 2
  2. 2025PRESCRIBE: Predicting Single-Cell Responses with Bayesian Estimationcited by 2
  3. 2025Uncertainty Quantification for Regression: A Unified Framework based on kernel scorescited by 2
  4. 2026Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3Rcited by 2
  5. 2022Uncertainty-Aware DNN for Multi-Modal Camera Localizationcited by 1
  6. 2025CARE: Confidence-Aware Regression Estimation of building density fine-tuning EO Foundation Modelscited by 1
  7. 2023Continuous Time Evidential Distributions for Irregular Time Seriescited by 0
  8. 2024Robust Calibration For Improved Weather Prediction Under Distributional Shiftcited by 0
  9. 2024Multivariate Bayesian Last Layer for Regression with Uncertainty Quantification and Decompositioncited by 0
  10. 2026Equivariant Evidential Deep Learning for Interatomic Potentialscited by 0
  11. 2026On the QUEST for Uncertainty Quantification via Highest Density Regionscited by 0