mlsanityData to 7 Oct 2026

Quantification of Uncertainty with Adversarial Models

arXiv 2307.03217 ↗First posted 6 Jul 2023cs.LG stat.MLcited by 28

Not on the map. Why?

Abstract (arXiv)

Quantifying uncertainty is important for actionable predictions in real-world applications. A crucial part of predictive uncertainty quantification is the estimation of epistemic uncertainty, which is defined as an integral of the product between a divergence function and the posterior. Current methods such as Deep Ensembles or MC dropout underperform at estimating the epistemic uncertainty, since they primarily consider the posterior when sampling models. We suggest Quantification of Uncertainty with Adversarial Models (QUAM) to better estimate the epistemic uncertainty. QUAM identifies regions where the whole product under the integral is large, not just the posterior. Consequently, QUAM has lower approximation error of the epistemic uncertainty compared to previous methods. Models for which the product is large correspond to adversarial models (not adversarial examples!). Adversarial models have both a high posterior as well as a high divergence between their predictions and that of a reference model. Our experiments show that QUAM excels in capturing epistemic uncertainty for deep learning models and outperforms previous methods on challenging tasks in the vision domain.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Builds on 59 of its 109 references that are in the map. First posted on arXiv 6 Jul 2023.

Builds on

59 of 109 references.

References · 59

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2017On Calibration of Modern Neural Networkscited by 4,860
  8. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  9. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  10. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,195
  11. 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
  12. 2017Axiomatic Attribution for Deep Networkscited by 3,350
38 more
  1. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  2. 2019Natural Adversarial Examplescited by 1,401
  3. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  4. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  5. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 813
  6. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  7. 2021A Survey of Uncertainty in Deep Neural Networkscited by 675
  8. 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
  9. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  10. 2015Weight Uncertainty in Neural Networkscited by 554
  11. 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
  12. 2019Deep Ensembles: A Loss Landscape Perspectivecited by 438
  13. 2018Deep Learning for Classical Japanese Literaturecited by 415
  14. 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
  15. 2022Last Layer Re-Training is Sufficient for Robustness to Spurious Correlationscited by 379
  16. 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
  17. 2017Snapshot Ensembles: Train 1, get M for freecited by 349
  18. 2020The Pitfalls of Simplicity Bias in Neural Networkscited by 349
  19. 2014Stochastic Gradient Hamiltonian Monte Carlocited by 341
  20. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 307
  21. 2020Pitfalls of In-Domain Uncertainty Estimation and Ensembling in Deep Learningcited by 208
  22. 2019Cyclical Stochastic Gradient MCMC for Bayesian Deep Learningcited by 203
  23. 2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
  24. 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
  25. 2018Understanding Measures of Uncertainty for Adversarial Example Detectioncited by 177
  26. 2015Preconditioned Stochastic Gradient Langevin Dynamics for Deep Neural Networkscited by 121
  27. 2022RAMBO-RL: Robust Adversarial Model-Based Offline Reinforcement Learningcited by 115
  28. 2021Repulsive Deep Ensembles are Bayesiancited by 103
  29. 2019DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networkscited by 92
  30. 2020Masksembles for Uncertainty Estimationcited by 88
  31. 2021On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertaintycited by 87
  32. 2019A Systematic Comparison of Bayesian Deep Learning Robustness in Diabetic Retinopathy Taskscited by 62
  33. 2021On the Practicality of Deterministic Epistemic Uncertaintycited by 62
  34. 2021Which Shortcut Cues Will DNNs Choose? A Study from the Parameter-Space Perspectivecited by 56
  35. 2020Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splittingcited by 54
  36. 2022Mechanistic Mode Connectivitycited by 50
  37. 2022Benchmarking Bayesian Deep Learning on Diabetic Retinopathy Detection Taskscited by 49
  38. 2017Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networkscited by 48

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 12; 2025: 12; 2026: 3.

28 papers.

Sort:

By area:

  1. 2024Rethinking Aleatoric and Epistemic Uncertaintycited by 40
  2. 2024Improving Uncertainty Estimation through Semantically Diverse Language Generationcited by 34
  3. 2023Introducing an Improved Information-Theoretic Measure of Predictive Uncertaintycited by 28
  4. 2024From Risk to Uncertainty: Generating Predictive Uncertainty Measures via Bayesian Estimationcited by 27
  5. 2024Rethinking Uncertainty Estimation in LLMs: A Principled Single-Sequence Measurecited by 18
  6. 2024On Information-Theoretic Measures of Predictive Uncertaintycited by 16
  7. 2025Uncertainty Quantification for Machine Learning in Healthcare: A Surveycited by 11
  8. 2024Epistemic Uncertainty Quantification For Pre-trained Neural Networkcited by 10
  9. 2025Uncertainty Quantification for Hallucination Detection in Large Language Models: Foundations, Methodology, and Future Directionscited by 10
  10. 2024Function Space Diversity for Uncertainty Prediction via Repulsive Last-Layer Ensemblescited by 8
  11. 2025Addressing Pitfalls in the Evaluation of Uncertainty Estimation Methods for Natural Language Generationcited by 7
  12. 2024Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Surveycited by 6
16 more
  1. 2024Achieving Well-Informed Decision-Making in Drug Discovery: A Comprehensive Calibration Study using Neural Network-Based Structure-Activity Modelscited by 2
  2. 2024The Disparate Benefits of Deep Ensemblescited by 2
  3. 2025Robust Adversarial Quantification via Conflict-Aware Evidential Deep Learningcited by 2
  4. 2024Probabilistic Scores of Classifiers, Calibration is not Enoughcited by 1
  5. 2025Temporal Distribution Shift in Real-World Pharmaceutical Data: Implications for Uncertainty Quantification in QSAR Modelscited by 1
  6. 2025Adversarial Examples in Environment Perception for Automated Driving (Review)cited by 1
  7. 2026A Ground-Truth Framework for Uncertainty Disentanglement with Posterior Riskcited by 1
  8. 2024PH-Dropout: Practical Epistemic Uncertainty Quantification for View Synthesiscited by 0
  9. 2025CONTINA: Confidence Interval for Traffic Demand Prediction with Coverage Guaranteecited by 0
  10. 2025Feature Fitted Online Conformal Prediction for Deep Time Series Forecasting Modelcited by 0
  11. 2025Objectomaly: Objectness-Aware Refinement for OoD Segmentation with Structural Consistency and Boundary Precisioncited by 0
  12. 2025PEdger++: Practical Edge Detection via Assembling Cross Informationcited by 0
  13. 2025Post-Hoc Split-Point Self-Consistency Verification for Efficient, Unified Quantification of Aleatoric and Epistemic Uncertainty in Deep Learningcited by 0
  14. 2025Guided Uncertainty Learning Using a Post-Hoc Evidential Meta-Modelcited by 0
  15. 2026Quantification of Uncertainty with Adversarial Models in Medical Image Segmentationcited by 0
  16. 2026Uncertainty quantification for trustworthy deep learning: Methods and measurescited by 0