mlsanityData to 7 Oct 2026

Probabilistic Circuits That Know What They Don't Know

arXiv 2302.06544 ↗First posted 13 Feb 2023cs.LG cs.AIcited by 7

Not on the map. Why?

Abstract (arXiv)

Probabilistic circuits (PCs) are models that allow exact and tractable probabilistic inference. In contrast to neural networks, they are often assumed to be well-calibrated and robust to out-of-distribution (OOD) data. In this paper, we show that PCs are in fact not robust to OOD data, i.e., they don't know what they don't know. We then show how this challenge can be overcome by model uncertainty quantification. To this end, we propose tractable dropout inference (TDI), an inference procedure to estimate uncertainty by deriving an analytical solution to Monte Carlo dropout (MCD) through variance propagation. Unlike MCD in neural networks, which comes at the cost of multiple network evaluations, TDI provides tractable sampling-free uncertainty estimates in a single forward pass. TDI improves the robustness of PCs to distribution shift and OOD data, demonstrated through a series of experiments evaluating the classification confidence and uncertainty estimates on real-world data.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Builds on 33 of its 67 references that are in the map. First posted on arXiv 13 Feb 2023.

Builds on

33 of 67 references.

References · 33

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017On Calibration of Modern Neural Networkscited by 4,860
  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. 2019Benchmarking Neural Network Robustness to Common Corruptions and Perturbationscited by 2,857
  6. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
  7. 2016Concrete Problems in AI Safetycited by 1,582
  8. 2015LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loopcited by 1,350
  9. 2019Normalizing Flows for Probabilistic Modeling and Inferencecited by 1,315
  10. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  11. 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
  12. 2017Deep Bayesian Active Learning with Image Datacited by 812
21 more
  1. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
  2. 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
  3. 2018Do Deep Generative Models Know What They Don't Know?cited by 443
  4. 2019Benchmarking Robustness in Object Detection: Autonomous Driving when Winter is Comingcited by 332
  5. 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 307
  6. 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
  7. 2015Bayesian SegNet: Model Uncertainty in Deep Convolutional Encoder-Decoder Architectures for Scene Understandingcited by 218
  8. 2021Epistemic Neural Networkscited by 120
  9. 2017Dropout Sampling for Robust Object Detection in Open-Set Conditionscited by 112
  10. 2020Einsum Networks: Fast and Scalable Learning of Tractable Probabilistic Circuitscited by 102
  11. 2019Uncertainty-guided Continual Learning with Bayesian Neural Networkscited by 100
  12. 2019Approximate Inference Turns Deep Networks into Gaussian Processescited by 89
  13. 2020Bayesian Deep Learning via Subnetwork Inferencecited by 85
  14. 2016Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriorscited by 82
  15. 2020Depth Uncertainty in Neural Networkscited by 56
  16. 2017Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networkscited by 48
  17. 2018SLANG: Fast Structured Covariance Approximations for Bayesian Deep Learning with Natural Gradientcited by 34
  18. 2019SPFlow: An Easy and Extensible Library for Deep Probabilistic Learning using Sum-Product Networkscited by 26
  19. 2019Unified Probabilistic Deep Continual Learning through Generative Replay and Open Set Recognitioncited by 26
  20. 2019Learning Logistic Circuitscited by 12
  21. 2021Handling Epistemic and Aleatory Uncertainties in Probabilistic Circuitscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 4; 2025: 1; 2026: 1.

7 papers.

  1. 2024Building Expressive and Tractable Probabilistic Generative Models: A Reviewcited by 12
  2. 2024A Unified Framework for Human-Allied Learning of Probabilistic Circuitscited by 5
  3. 2025Tractable Representation Learning with Probabilistic Circuitscited by 4
  4. 2024chiSPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domainscited by 3
  5. 2024On Hardware-efficient Inference in Probabilistic Circuitscited by 1
  6. 2026Geometry-Aware Probabilistic Circuits via Voronoi Tessellationscited by 1
  7. 2023Pruning-Based Extraction of Descriptions from Probabilistic Circuitscited by 0