Uncertainty Calibration in Bayesian Neural Networks via Distance-Aware Priors
Not on the map. Why?
Abstract (arXiv)
As we move away from the data, the predictive uncertainty should increase, since a great variety of explanations are consistent with the little available information. We introduce Distance-Aware Prior (DAP) calibration, a method to correct overconfidence of Bayesian deep learning models outside of the training domain. We define DAPs as prior distributions over the model parameters that depend on the inputs through a measure of their distance from the training set. DAP calibration is agnostic to the posterior inference method, and it can be performed as a post-processing step. We demonstrate its effectiveness against several baselines in a variety of classification and regression problems, including benchmarks designed to test the quality of predictive distributions away from the data.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 31 of its 53 references that are in the map. First posted on arXiv 17 Jul 2022.
Builds on
31 of 53 references.
References · 31
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2017On Calibration of Modern Neural Networkscited by 4,860
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2013Auto-Encoding Variational Bayescited by 3,980
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,888
- 2016Wide Residual Networkscited by 3,057
- 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,335
- 2017Improved Training of Wasserstein GANscited by 2,223
- 2015Variational Inference with Normalizing Flowscited by 2,161
- 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
- 2016Variational Inference: A Review for Statisticianscited by 1,466
19 more
- 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,325
- 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 903
- 2018Predictive Uncertainty Estimation via Prior Networkscited by 555
- 2019A Simple Baseline for Bayesian Uncertainty in Deep Learningcited by 555
- 2020Bayesian Deep Learning and a Probabilistic Perspective of Generalizationcited by 480
- 2015Deep Kernel Learningcited by 440
- 2018Accurate Uncertainties for Deep Learning Using Calibrated Regressioncited by 417
- 2020Simple and Principled Uncertainty Estimation with Deterministic Deep Learning via Distance Awarenesscited by 389
- 2021Laplace Redux -- Effortless Bayesian Deep Learningcited by 359
- 2021What Are Bayesian Neural Network Posteriors Really Like?cited by 307
- 2019Cyclical Stochastic Gradient MCMC for Bayesian Deep Learningcited by 203
- 2019Practical Deep Learning with Bayesian Principlescited by 158
- 2016Stochastic Variational Deep Kernel Learningcited by 92
- 2021On Feature Collapse and Deep Kernel Learning for Single Forward Pass Uncertaintycited by 87
- 2019'In-Between' Uncertainty in Bayesian Neural Networkscited by 79
- 2019Quality of Uncertainty Quantification for Bayesian Neural Network Inferencecited by 58
- 2022On Uncertainty, Tempering, and Data Augmentation in Bayesian Classificationcited by 46
- 2021Dangers of Bayesian Model Averaging under Covariate Shiftcited by 31
- 2019Conformal calibratorscited by 22
Built on by
Citing papers per year: 2024: 1; 2025: 2.
3 papers.