Pith. sign in

REVIEW 8 cited by

Weight Uncertainty in Neural Networks

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 1505.05424 v2 pith:VGKJDVVO submitted 2015-05-20 stat.ML cs.LG

Weight Uncertainty in Neural Networks

classification stat.ML cs.LG
keywords uncertaintyweightslearningneuralprincipledusedweightalgorithm
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

We introduce a new, efficient, principled and backpropagation-compatible algorithm for learning a probability distribution on the weights of a neural network, called Bayes by Backprop. It regularises the weights by minimising a compression cost, known as the variational free energy or the expected lower bound on the marginal likelihood. We show that this principled kind of regularisation yields comparable performance to dropout on MNIST classification. We then demonstrate how the learnt uncertainty in the weights can be used to improve generalisation in non-linear regression problems, and how this weight uncertainty can be used to drive the exploration-exploitation trade-off in reinforcement learning.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Concrete Problems in AI Safety

    cs.AI 2016-06 accept novelty 7.0

    The paper categorizes five concrete AI safety problems arising from flawed objectives, costly evaluation, and learning dynamics.

  2. Unsupervised Domain Adaptation via Calibrating Uncertainties

    cs.LG 2019-07 unverdicted novelty 6.0

    A new regularization approach for unsupervised domain adaptation that calibrates Renyi entropy of uncertainties estimated via variational Bayes.

  3. Bayesian Inference with Shaped Deep Non-linear MLPs

    math.ST 2026-05 unverdicted novelty 5.0

    In the LP/N = Θ(1) regime, Bayesian predictive posteriors for deep MLPs equal those of data-dependent kernels to first order, with a criterion identifying data processes that benefit from larger effective depth.

  4. A Framework for Variational Inference of Lightweight Bayesian Neural Networks with Heteroscedastic Uncertainties

    cs.LG 2024-02 unverdicted novelty 5.0

    Framework embeds aleatoric and epistemic uncertainties into BNN parameter variances and applies moment propagation for sampling-free variational inference in lightweight networks.

  5. Comparing Semi-Parametric Model Learning Algorithms for Dynamic Model Estimation in Robotics

    stat.ML 2019-06 unverdicted novelty 5.0

    Semi-parametric Gaussian process regression yields the most accurate inverse dynamics models in most tested robotic scenarios compared to parametric, non-parametric, and other semi-parametric baselines.

  6. Quality of Uncertainty Quantification for Bayesian Neural Network Inference

    cs.LG 2019-06 unverdicted novelty 5.0

    Empirical comparison of ten BNN inference methods shows test log-likelihood can mislead on uncertainty quality and that posterior-structure innovations do not necessarily yield high-quality approximations.

  7. Portfolio Optimization Proxies under Label Scarcity and Regime Shifts via Bayesian and Deterministic Students under Semi-Supervised Sandwich Training

    cs.LG 2026-04 unverdicted novelty 4.0

    A semi-supervised teacher-student framework enables neural networks to proxy CVaR portfolio optimization using synthetic data augmentation for scarce labels and regime shifts.

  8. Bayesian Neural Networks: An Introduction and Survey

    stat.ML 2020-06 unverdicted novelty 1.0

    A survey introducing Bayesian Neural Networks and comparing approximate inference methods to enable uncertainty quantification in neural network predictions.