mlsanityData to 7 Oct 2026

Nonparametric Uncertainty Quantification for Single Deterministic Neural Network

arXiv 2202.03101 ↗First posted 7 Feb 2022stat.ML cs.LGcited by 36

Not on the map. Why?

Abstract (arXiv)

This paper proposes a fast and scalable method for uncertainty quantification of machine learning models' predictions. First, we show the principled way to measure the uncertainty of predictions for a classifier based on Nadaraya-Watson's nonparametric estimate of the conditional label distribution. Importantly, the proposed approach allows to disentangle explicitly aleatoric and epistemic uncertainties. The resulting method works directly in the feature space. However, one can apply it to any neural network by considering an embedding of the data induced by the network. We demonstrate the strong performance of the method in uncertainty estimation tasks on text classification problems and a variety of real-world image datasets, such as MNIST, SVHN, CIFAR-100 and several versions of ImageNet.

Key facts. Cited by 36 papers in the map (data through 7 Oct 2026). Builds on 29 of its 84 references that are in the map. First posted on arXiv 7 Feb 2022.

Builds on

29 of 84 references.

References · 29

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  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. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,665
  5. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  6. 2015Variational Inference with Normalizing Flowscited by 2,161
  7. 2016Density estimation using Real NVPcited by 2,029
  8. 2020The Many Faces of Robustness: A Critical Analysis of Out-of-Distribution Generalizationcited by 1,842
  9. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  10. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  11. 2016Variational Inference: A Review for Statisticianscited by 1,466
  12. 2019Natural Adversarial Examplescited by 1,401
17 more
  1. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  2. 2020Energy-based Out-of-distribution Detectioncited by 1,296
  3. 2018Neural Network Acceptability Judgmentscited by 952
  4. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  5. 2017Deep Bayesian Active Learning with Image Datacited by 812
  6. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  7. 2018Evidential Deep Learning to Quantify Classification Uncertaintycited by 728
  8. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  9. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  10. 2019An Evaluation Dataset for Intent Classification and Out-of-Scope Predictioncited by 378
  11. 2019SelectiveNet: A Deep Neural Network with an Integrated Reject Optioncited by 333
  12. 2018Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problemcited by 323
  13. 2019Ensemble Distribution Distillationcited by 158
  14. 2020Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts?cited by 139
  15. 2020Greedy Policy Search: A Simple Baseline for Learnable Test-Time Augmentationcited by 61
  16. 2019Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection In Task Oriented Dialogcited by 33
  17. 2018Uncertainty Modelling in Deep Networks: Forecasting Short and Noisy Seriescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 15; 2025: 11; 2026: 5.

36 papers.

Sort:

By area:

  1. 2024Fact-Checking the Output of Large Language Models via Token-Level Uncertainty Quantificationcited by 159
  2. 2023LM-Polygraph: Uncertainty Estimation for Language Modelscited by 130
  3. 2024Benchmarking Uncertainty Quantification Methods for Large Language Models with LM-Polygraphcited by 105
  4. 2023A Survey on Uncertainty Quantification Methods for Deep Learningcited by 78
  5. 2024Rethinking Aleatoric and Epistemic Uncertaintycited by 40
  6. 2025Uncertainty Quantification for LLMs through Minimum Bayes Risk: Bridging Confidence and Consistencycited by 30
  7. 2024From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimationcited by 27
  8. 2025Position: Uncertainty Quantification Needs Reassessment for Large-language Model Agentscited by 27
  9. 2024Uncertainty Estimation by Density Aware Evidential Deep Learningcited by 22
  10. 2025Token-Level Density-Based Uncertainty Quantification Methods for Eliciting Truthfulness of Large Language Modelscited by 18
  11. 2024On Information-Theoretic Measures of Predictive Uncertaintycited by 16
  12. 2026Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunitiescited by 15
24 more
  1. 2023A Data-Driven Measure of Relative Uncertainty for Misclassification Detectioncited by 14
  2. 2023Density-Softmax: Efficient Test-time Model for Uncertainty Estimation and Robustness under Distribution Shiftscited by 12
  3. 2025Uncertainty Quantification with the Empirical Neural Tangent Kernelcited by 11
  4. 2025Uncertainty Estimation by Flexible Evidential Deep Learningcited by 10
  5. 2024Density-Regression: Efficient and Distance-Aware Deep Regressor for Uncertainty Estimation under Distribution Shiftscited by 7
  6. 2024Tilt your Head: Activating the Hidden Spatial-Invariance of Classifierscited by 7
  7. 2025Uncertainty-aware abstention in medical diagnosis based on medical textscited by 6
  8. 2025Uncertainty Quantification for Regression using Proper Scoring Rulescited by 5
  9. 2024Unsupervised Variational Translator for Bridging Image Restoration and High-Level Vision Taskscited by 3
  10. 2024Holistic Uncertainty Estimation For Open-Set Recognitioncited by 3
  11. 2024Beyond the Norms: Detecting Prediction Errors in Regression Modelscited by 2
  12. 2025Uncertainty Quantification for Regression: A Unified Framework based on kernel scorescited by 2
  13. 2023Learning Invariant Representations with a Nonparametric Nadaraya-Watson Headcited by 1
  14. 2024Combining Statistical Depth and Fermat Distance for Uncertainty Quantificationcited by 1
  15. 2024Efficient Nearest Neighbor based Uncertainty Estimation for Natural Language Processing Taskscited by 1
  16. 2024Integrating uncertainty quantification into randomized smoothing based robustness guaranteescited by 1
  17. 2024Probabilistic Modeling of Disparity Uncertainty for Robust and Efficient Stereo Matchingcited by 1
  18. 2025Who to Trust? Aggregating Client Predictions in Federated Distillationcited by 1
  19. 2025Multidimensional Uncertainty Quantification via Optimal Transportcited by 1
  20. 2026Subjective Risk Decomposition: A New View for Uncertainty Quantificationcited by 1
  21. 2026A Ground-Truth Framework for Uncertainty Disentanglement with Posterior Riskcited by 1
  22. 2025Trustworthy Quantum Machine Learning: A Roadmap for Reliability, Robustness, and Security in the NISQ Eracited by 0
  23. 2026Synthesizing real-world distributions from high-dimensional Gaussian Noise with Fully Connected Neural Networkcited by 0
  24. 2026Uncertainty Estimation via Hyperspherical Confidence Mappingcited by 0