Understanding the Trade-offs in Accuracy and Uncertainty Quantification: Architecture and Inference Choices in Bayesian Neural Networks

• URL: http://arxiv.org/abs/2503.11808v2
• Date: Tue, 17 Jun 2025 16:07:13 GMT
• Title: Understanding the Trade-offs in Accuracy and Uncertainty Quantification: Architecture and Inference Choices in Bayesian Neural Networks
• Authors: Alisa Sheinkman, Sara Wade,
• Abstract summary: Despite promising theoretical results, the properties of even the most commonly used posterior approximations are often questioned.<n>The dimensions of modern deep models, coupled with the lack of identifiability, make Markov chain Monte Carlo (MCMC) unable to fully explore the posterior.<n> variational inference benefits from improved computational complexity but lacks the multimodalal guarantees of sampling-based inference.<n> stacking and ensembles of variational approximations provided comparable accuracy to MCMC at a much-reduced cost.
• Score: 0.276240219662896
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As modern neural networks get more complex, specifying a model with high predictive performance and sound uncertainty quantification becomes a more challenging task. Despite some promising theoretical results on the true posterior predictive distribution of Bayesian neural networks, the properties of even the most commonly used posterior approximations are often questioned. Computational burdens and intractable posteriors expose miscalibrated Bayesian neural networks to poor accuracy and unreliable uncertainty estimates. Approximate Bayesian inference aims to replace unknown and intractable posterior distributions with some simpler but feasible distributions. The dimensions of modern deep models, coupled with the lack of identifiability, make Markov chain Monte Carlo (MCMC) tremendously expensive and unable to fully explore the multimodal posterior. On the other hand, variational inference benefits from improved computational complexity but lacks the asymptotical guarantees of sampling-based inference and tends to concentrate around a single mode. The performance of both approaches heavily depends on architectural choices; this paper aims to shed some light on this by considering the computational costs, accuracy and uncertainty quantification in different scenarios including large width and out-of-sample data. To improve posterior exploration, different model averaging and ensembling techniques are studied, along with their benefits on predictive performance. In our experiments, variational inference overall provided better uncertainty quantification than MCMC; further, stacking and ensembles of variational approximations provided comparable accuracy to MCMC at a much-reduced cost.

Related papers

• Cooperative Bayesian and variance networks disentangle aleatoric and epistemic uncertainties [0.0]
  Real-world data contains aleatoric uncertainty - irreducible noise arising from imperfect measurements or from incomplete knowledge about the data generation process.<n>Mean variance estimation (MVE) networks can learn this type of uncertainty but require ad-hoc regularization strategies to avoid overfitting.<n>We propose to train a variance network with a Bayesian neural network and demonstrate that the resulting model disentangles aleatoric and epistemic uncertainties while improving the mean estimation.
  arXiv  Detail & Related papers  (2025-05-05T15:50:52Z)
• Quantification of Uncertainties in Probabilistic Deep Neural Network by Implementing Boosting of Variational Inference [0.38366697175402226]
  Boosted Bayesian Neural Networks (BBNN) is a novel approach that enhances neural network weight distribution approximations. BBNN achieves 5% higher accuracy compared to conventional neural networks.
  arXiv  Detail & Related papers  (2025-03-18T05:11:21Z)
• Variational Bayesian Bow tie Neural Networks with Shrinkage [0.276240219662896]
  We build a relaxed version of the standard feed-forward rectified neural network. We employ Polya-Gamma data augmentation tricks to render a conditionally linear and Gaussian model. We derive a variational inference algorithm that avoids distributional assumptions and independence across layers.
  arXiv  Detail & Related papers  (2024-11-17T17:36:30Z)
• Estimating Epistemic and Aleatoric Uncertainty with a Single Model [5.871583927216653]
  We introduce a new approach to ensembling, hyper-diffusion models (HyperDM) HyperDM offers prediction accuracy on par with, and in some cases superior to, multi-model ensembles. We validate our method on two distinct real-world tasks: x-ray computed tomography reconstruction and weather temperature forecasting.
  arXiv  Detail & Related papers  (2024-02-05T19:39:52Z)
• Implicit Variational Inference for High-Dimensional Posteriors [7.924706533725115]
  In variational inference, the benefits of Bayesian models rely on accurately capturing the true posterior distribution. We propose using neural samplers that specify implicit distributions, which are well-suited for approximating complex multimodal and correlated posteriors. Our approach introduces novel bounds for approximate inference using implicit distributions by locally linearising the neural sampler.
  arXiv  Detail & Related papers  (2023-10-10T14:06:56Z)
• Collapsed Inference for Bayesian Deep Learning [36.1725075097107]
  We introduce a novel collapsed inference scheme that performs Bayesian model averaging using collapsed samples. A collapsed sample represents uncountably many models drawn from the approximate posterior. Our proposed use of collapsed samples achieves a balance between scalability and accuracy.
  arXiv  Detail & Related papers  (2023-06-16T08:34:42Z)
• Single Model Uncertainty Estimation via Stochastic Data Centering [39.71621297447397]
  We are interested in estimating the uncertainties of deep neural networks. We present a striking new finding that an ensemble of neural networks with the same weight initialization, trained on datasets that are shifted by a constant bias gives rise to slightly inconsistent trained models. We show that $Delta-$UQ's uncertainty estimates are superior to many of the current methods on a variety of benchmarks.
  arXiv  Detail & Related papers  (2022-07-14T23:54:54Z)
• NUQ: Nonparametric Uncertainty Quantification for Deterministic Neural Networks [151.03112356092575]
  We show the principled way to measure the uncertainty of predictions for a classifier based on Nadaraya-Watson's nonparametric estimate of the conditional label distribution. We demonstrate the strong performance of the method in uncertainty estimation tasks on a variety of real-world image datasets.
  arXiv  Detail & Related papers  (2022-02-07T12:30:45Z)
• Predicting with Confidence on Unseen Distributions [90.68414180153897]
  We connect domain adaptation and predictive uncertainty literature to predict model accuracy on challenging unseen distributions. We find that the difference of confidences (DoC) of a classifier's predictions successfully estimates the classifier's performance change over a variety of shifts. We specifically investigate the distinction between synthetic and natural distribution shifts and observe that despite its simplicity DoC consistently outperforms other quantifications of distributional difference.
  arXiv  Detail & Related papers  (2021-07-07T15:50:18Z)
• What Are Bayesian Neural Network Posteriors Really Like? [63.950151520585024]
  We show that Hamiltonian Monte Carlo can achieve significant performance gains over standard and deep ensembles. We also show that deep distributions are similarly close to HMC as standard SGLD, and closer than standard variational inference.
  arXiv  Detail & Related papers  (2021-04-29T15:38:46Z)
• Improving Uncertainty Calibration via Prior Augmented Data [56.88185136509654]
  Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. They are often overconfident in their predictions, which leads to inaccurate and miscalibrated probabilistic predictions. We propose a solution by seeking out regions of feature space where the model is unjustifiably overconfident, and conditionally raising the entropy of those predictions towards that of the prior distribution of the labels.
  arXiv  Detail & Related papers  (2021-02-22T07:02:37Z)
• Unlabelled Data Improves Bayesian Uncertainty Calibration under Covariate Shift [100.52588638477862]
  We develop an approximate Bayesian inference scheme based on posterior regularisation. We demonstrate the utility of our method in the context of transferring prognostic models of prostate cancer across globally diverse populations.
  arXiv  Detail & Related papers  (2020-06-26T13:50:19Z)
• Stacking for Non-mixing Bayesian Computations: The Curse and Blessing of Multimodal Posteriors [8.11978827493967]
  We propose an approach using parallel runs of MCMC, variational, or mode-based inference to hit as many modes as possible. We present theoretical consistency with an example where the stacked inference process approximates the true data. We demonstrate practical implementation in several model families.
  arXiv  Detail & Related papers  (2020-06-22T15:26:59Z)
• Diversity inducing Information Bottleneck in Model Ensembles [73.80615604822435]
  In this paper, we target the problem of generating effective ensembles of neural networks by encouraging diversity in prediction. We explicitly optimize a diversity inducing adversarial loss for learning latent variables and thereby obtain diversity in the output predictions necessary for modeling multi-modal data. Compared to the most competitive baselines, we show significant improvements in classification accuracy, under a shift in the data distribution.
  arXiv  Detail & Related papers  (2020-03-10T03:10:41Z)
• Being Bayesian, Even Just a Bit, Fixes Overconfidence in ReLU Networks [65.24701908364383]
  We show that a sufficient condition for a uncertainty on a ReLU network is "to be a bit Bayesian calibrated" We further validate these findings empirically via various standard experiments using common deep ReLU networks and Laplace approximations.
  arXiv  Detail & Related papers  (2020-02-24T08:52:06Z)
• Bayesian Deep Learning and a Probabilistic Perspective of Generalization [56.69671152009899]
  We show that deep ensembles provide an effective mechanism for approximate Bayesian marginalization. We also propose a related approach that further improves the predictive distribution by marginalizing within basins of attraction.
  arXiv  Detail & Related papers  (2020-02-20T15:13:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.