Data to 7 Oct 2026

Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks

arXiv 1502.05336 ↗First posted 18 Feb 2015stat.MLcited by 295

Not on the map. Why?

Abstract (arXiv)

Large multilayer neural networks trained with backpropagation have recently achieved state-of-the-art results in a wide range of problems. However, using backprop for neural net learning still has some disadvantages, e.g., having to tune a large number of hyperparameters to the data, lack of calibrated probabilistic predictions, and a tendency to overfit the training data. In principle, the Bayesian approach to learning neural networks does not have these problems. However, existing Bayesian techniques lack scalability to large dataset and network sizes. In this work we present a novel scalable method for learning Bayesian neural networks, called probabilistic backpropagation (PBP). Similar to classical backpropagation, PBP works by computing a forward propagation of probabilities through the network and then doing a backward computation of gradients. A series of experiments on ten real-world datasets show that PBP is significantly faster than other techniques, while offering competitive predictive abilities. Our experiments also show that PBP provides accurate estimates of the posterior variance on the network weights.

Key facts. Cited by 295 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Feb 2015.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 73; 2022: 68; 2023: 51; 2024: 42; 2025: 40; 2026: 20.

295 papers.

Sort:

By area:

2021A Survey of Uncertainty in Deep Neural Networkscited by 675
2018Scalable agent alignment via reward modeling: a research directioncited by 438
2021What Are Bayesian Neural Network Posteriors Really Like?cited by 307
2023Generating with Confidence: Uncertainty Quantification for Black-box Large Language Modelscited by 286
2021Deep Deterministic Uncertainty: A Simple Baselinecited by 200
2021Bayesian Neural Network Priors Revisitedcited by 121
2022On the Pitfalls of Heteroscedastic Uncertainty Estimation with Probabilistic Neural Networkscited by 119
2021Scalable Marginal Likelihood Estimation for Model Selection in Deep Learningcited by 105
2022CARD: Classification and Regression Diffusion Modelscited by 102
2021Priors in Bayesian Deep Learning: A Reviewcited by 101
2021The Bayesian Learning Rulecited by 95
2021The Devil is in the Margin: Margin-based Label Smoothing for Network Calibrationcited by 91

38 more

2021Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representationscited by 80
2022Recent Advances in Bayesian Optimizationcited by 74
2021Prior and Posterior Networks: A Survey on Evidential Deep Learning Methods For Uncertainty Estimationcited by 71
2024Uncertainty-aware Reward Model: Teaching Reward Models to Know What is Unknowncited by 71
2022Agree to Disagree: Diversity through Disagreement for Better Transferabilitycited by 69
2021Inconsistency-aware Uncertainty Estimation for Semi-supervised Medical Image Segmentationcited by 61
2023Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimizationcited by 57
2021Few-shot Conformal Prediction with Auxiliary Taskscited by 53
2022Packed-Ensembles for Efficient Uncertainty Estimationcited by 49
2024Improved off-policy training of diffusion samplerscited by 47
2022A Langevin-like Sampler for Discrete Distributionscited by 42
2021Trustworthy Multimodal Regression with Mixture of Normal-inverse Gamma Distributionscited by 39
2022What Makes Graph Neural Networks Miscalibrated?cited by 39
2022Predictive Inference with Feature Conformal Predictioncited by 33
2021AutoDEUQ: Automated Deep Ensemble with Uncertainty Quantificationcited by 31
2023BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inferencecited by 30
2021Variational Refinement for Importance Sampling Using the Forward Kullback-Leibler Divergencecited by 29
2022Adapting the Linearised Laplace Model Evidence for Modern Deep Learningcited by 29
2022Conformal Prediction Sets with Limited False Positivescited by 28
2021From partners to populations: A hierarchical Bayesian account of coordination and conventioncited by 27
2022Accelerated Linearized Laplace Approximation for Bayesian Deep Learningcited by 27
2023A Primer on Bayesian Neural Networks: Review and Debatescited by 26
2024A Comprehensive Survey on Evidential Deep Learning and Its Applicationscited by 25
2021Locally Valid and Discriminative Prediction Intervals for Deep Learning Modelscited by 24
2022MUAD: Multiple Uncertainties for Autonomous Driving, a benchmark for multiple uncertainty types and taskscited by 24
2022Bayesian autoencoders for data-driven discovery of coordinates, governing equations and fundamental constantscited by 24
2025Understanding the Uncertainty of LLM Explanations: A Perspective Based on Reasoning Topologycited by 24
2025TokUR: Token-Level Uncertainty Estimation for Large Language Model Reasoningcited by 24
2023Low-rank extended Kalman filtering for online learning of neural networks from streaming datacited by 23
2021Efficient and Robust LiDAR-Based End-to-End Navigationcited by 22
2021Detecting Concept Drift With Neural Network Model Uncertaintycited by 21
2022Region-Based Evidential Deep Learning to Quantify Uncertainty and Improve Robustness of Brain Tumor Segmentationcited by 20
2023Treatment-aware Diffusion Probabilistic Model for Longitudinal MRI Generation and Diffuse Glioma Growth Predictioncited by 19
2022Variational Model Perturbation for Source-Free Domain Adaptationcited by 18
2022Latent Discriminant deterministic Uncertaintycited by 17
2023Optimal Training of Mean Variance Estimation Neural Networkscited by 17
2021Learning Prediction Intervals for Regression: Generalization and Calibrationcited by 16
2021NOMU: Neural Optimization-based Model Uncertaintycited by 16

50 most cited of 295 All 295 (JSON)