mlsanityData to 7 Oct 2026

Is MC Dropout Bayesian?

arXiv 2110.04286 ↗First posted 8 Oct 2021cs.LG stat.MLcited by 35

Not on the map. Why?

Abstract (arXiv)

MC Dropout is a mainstream "free lunch" method in medical imaging for approximate Bayesian computations (ABC). Its appeal is to solve out-of-the-box the daunting task of ABC and uncertainty quantification in Neural Networks (NNs); to fall within the variational inference (VI) framework; and to propose a highly multimodal, faithful predictive posterior. We question the properties of MC Dropout for approximate inference, as in fact MC Dropout changes the Bayesian model; its predictive posterior assigns 0 probability to the true model on closed-form benchmarks; the multimodality of its predictive posterior is not a property of the true predictive posterior but a design artefact. To address the need for VI on arbitrary models, we share a generic VI engine within the pytorch framework. The code includes a carefully designed implementation of structured (diagonal plus low-rank) multivariate normal variational families, and mixtures thereof. It is intended as a go-to no-free-lunch approach, addressing shortcomings of mean-field VI with an adjustable trade-off between expressivity and computational complexity.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 11 of its 26 references that are in the map. First posted on arXiv 8 Oct 2021.

Builds on

11 of 26 references.

References · 11

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  2. 2015Weight Uncertainty in Neural Networkscited by 554
  3. 2017Advances in Variational Inferencecited by 236
  4. 2013Expectation Propagation for approximate Bayesian inferencecited by 172
  5. 2017Multiplicative Normalizing Flows for Variational Bayesian Neural Networkscited by 157
  6. 2018A Unified Particle-Optimization Framework for Scalable Bayesian Samplingcited by 44
  7. 2017Variational Inference using Implicit Distributionscited by 39
  8. 2016Variational Boosting: Iteratively Refining Posterior Approximationscited by 36
  9. 2015Bridging the Gap between Stochastic Gradient MCMC and Stochastic Optimizationcited by 17
  10. 2018Meta-Learning for Stochastic Gradient MCMCcited by 16
  11. 2017Hierarchical Implicit Models and Likelihood-Free Variational Inferencecited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 8; 2024: 13; 2025: 6; 2026: 4.

35 papers.

Sort:

By area:

  1. 2023A Primer on Bayesian Neural Networks: Review and Debatescited by 26
  2. 2022GFlowOut: Dropout with Generative Flow Networkscited by 22
  3. 2022Efficient Bayesian Uncertainty Estimation for nnU-Netcited by 19
  4. 2024Conformal Prediction for Causal Effects of Continuous Treatmentscited by 19
  5. 2024DiffPO: A causal diffusion model for learning distributions of potential outcomescited by 17
  6. 2023That Label's Got Style: Handling Label Style Bias for Uncertain Image Segmentationcited by 13
  7. 2024Data-Driven Physics-Informed Neural Networks: A Digital Twin Perspectivecited by 12
  8. 2025Uncertainty Quantification with the Empirical Neural Tangent Kernelcited by 11
  9. 2023Body Knowledge and Uncertainty Modeling for Monocular 3D Human Body Reconstructioncited by 8
  10. 2024A Review of Bayesian Uncertainty Quantification in Deep Probabilistic Image Segmentationcited by 6
  11. 2022Bayesian posterior approximation with stochastic ensemblescited by 5
  12. 2024An uncertainty-aware Digital Shadow for underground multimodal CO2 storage monitoringcited by 5
23 more
  1. 2025Split Conformal Prediction in the Function Space with Neural Operatorscited by 4
  2. 2023Towards Reliable Uncertainty Quantification via Deep Ensembles in Multi-output Regression Taskcited by 3
  3. 2023Inter-Rater Uncertainty Quantification in Medical Image Segmentation via Rater-Specific Bayesian Neural Networkscited by 3
  4. 2024Neural Network Prediction of Strong Lensing Systems with Domain Adaptation and Uncertainty Quantificationcited by 2
  5. 2024Why you don't overfit, and don't need Bayes if you only train for one epochcited by 2
  6. 2025Generation Space Size: Understanding and Calibrating Open-Endedness of LLM Generationscited by 2
  7. 2025Unreliable Uncertainty Estimates with Monte Carlo Dropoutcited by 2
  8. 2022Propagating Variational Model Uncertainty for Bioacoustic Call Label Smoothingcited by 1
  9. 2023Distance Preserving Machine Learning for Uncertainty Aware Accelerator Capacitance Predictionscited by 1
  10. 2023Out-of-distribution Object Detection through Bayesian Uncertainty Estimationcited by 1
  11. 2024Enhance Eye Disease Detection using Learnable Probabilistic Discrete Latents in Machine Learning Architecturescited by 1
  12. 2024Bayesian Uncertainty Estimation by Hamiltonian Monte Carlo: Applications to Cardiac MRI Segmentationcited by 1
  13. 2026TRIE: An Evaluation Framework for Stochastic PDE Surrogatescited by 1
  14. 2023Bayesian Neural Networks for 2D MRI Segmentationcited by 0
  15. 2024BayesJudge: Bayesian Kernel Language Modelling with Confidence Uncertainty in Legal Judgment Predictioncited by 0
  16. 2024On Uniform, Bayesian, and PAC-Bayesian Deep Ensemblescited by 0
  17. 2024Taylor-Sensus Network: Embracing Noise to Enlighten Uncertainty for Scientific Datacited by 0
  18. 2024Fine-Grained Uncertainty Quantification via Collisionscited by 0
  19. 2025Principled Input-Output-Conditioned Post-Hoc Uncertainty Estimation for Regression Networkscited by 0
  20. 2025Uncertainty Tube Visualization of Particle Trajectoriescited by 0
  21. 2026Calibrated uncertainty quantification for prosumer flexibility aggregation in ancillary service marketscited by 0
  22. 2026Robust Uncertainty Estimation under Distribution Shift via Difference Reconstructioncited by 0
  23. 2026CUPID: A Plug-in Framework for Joint Aleatoric and Epistemic Uncertainty Estimation with a Single Modelcited by 0