mlsanityData to 7 Oct 2026

What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization

arXiv 2207.05161 ↗First posted 11 Jul 2022cs.LG cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Uncertainty Quantification (UQ) is essential for creating trustworthy machine learning models. Recent years have seen a steep rise in UQ methods that can flag suspicious examples, however, it is often unclear what exactly these methods identify. In this work, we propose a framework for categorizing uncertain examples flagged by UQ methods in classification tasks. We introduce the confusion density matrix -- a kernel-based approximation of the misclassification density -- and use this to categorize suspicious examples identified by a given uncertainty method into three classes: out-of-distribution (OOD) examples, boundary (Bnd) examples, and examples in regions of high in-distribution misclassification (IDM). Through extensive experiments, we show that our framework provides a new and distinct perspective for assessing differences between uncertainty quantification methods, thereby forming a valuable assessment benchmark.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 31 of its 56 references that are in the map. First posted on arXiv 11 Jul 2022.

Builds on

31 of 56 references.

References · 31

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  5. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  6. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  7. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  8. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,472
  9. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  10. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  11. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  12. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
19 more
  1. 2019Likelihood Ratios for Out-of-Distribution Detectioncited by 451
  2. 2017On the Properties of the Softmax Function with Application in Game Theory and Reinforcement Learningcited by 136
  3. 2017Interpretable Learning for Self-Driving Cars by Visualizing Causal Attentioncited by 106
  4. 2020Are Labels Always Necessary for Classifier Accuracy Evaluation?cited by 104
  5. 2020From ImageNet to Image Classification: Contextualizing Progress on Benchmarkscited by 90
  6. 2022Rethinking Goal-conditioned Supervised Learning and Its Connection to Offline RLcited by 89
  7. 2022RORL: Robust Offline Reinforcement Learning via Conservative Smoothingcited by 83
  8. 2019Quality of Uncertainty Quantification for Bayesian Neural Network Inferencecited by 58
  9. 2019Risk-Averse Trust Region Optimization for Reward-Volatility Reductioncited by 53
  10. 2021Generating Interpretable Counterfactual Explanations By Implicit Minimisation of Epistemic and Aleatoric Uncertaintiescited by 41
  11. 2018Structured Variational Learning of Bayesian Neural Networks with Horseshoe Priorscited by 35
  12. 2021Explaining Latent Representations with a Corpus of Examplescited by 30
  13. 2019Density estimation in representation space to predict model uncertaintycited by 27
  14. 2020Detecting Out-of-distribution Samples via Variational Auto-encoder with Reliable Uncertainty Estimationcited by 24
  15. 2021Uncertainty Quantification 360: A Holistic Toolkit for Quantifying and Communicating the Uncertainty of AIcited by 22
  16. 2020Notes on the Behavior of MC Dropoutcited by 21
  17. 2019Empirical Study of Easy and Hard Examples in CNN Trainingcited by 9
  18. 2018Can Deep Learning Predict Risky Retail Investors? A Case Study in Financial Risk Behavior Forecastingcited by 7
  19. 2019MPP: Model Performance Predictorcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 3.

5 papers.

  1. 2023A Survey of Confidence Estimation and Calibration in Large Language Modelscited by 253
  2. 2024Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AIcited by 11
  3. 2025Uncertainty Reasoning with Photonic Bayesian Machinescited by 3
  4. 2025Finer Disentanglement of Aleatoric Uncertainty Can Accelerate Chemical Histopathology Imagingcited by 1
  5. 2025Disentangling Uncertainties by Learning Compressed Data Representationcited by 1