mlsanityData to 14 Oct 2026

Implicit Weight Uncertainty in Neural Networks

arXiv 1711.01297 ↗First posted 3 Nov 2017stat.ML cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

Modern neural networks tend to be overconfident on unseen, noisy or incorrectly labelled data and do not produce meaningful uncertainty measures. Bayesian deep learning aims to address this shortcoming with variational approximations (such as Bayes by Backprop or Multiplicative Normalising Flows). However, current approaches have limitations regarding flexibility and scalability. We introduce Bayes by Hypernet (BbH), a new method of variational approximation that interprets hypernetworks as implicit distributions. It naturally uses neural networks to model arbitrarily complex distributions and scales to modern deep learning architectures. In our experiments, we demonstrate that our method achieves competitive accuracies and predictive uncertainties on MNIST and a CIFAR5 task, while being the most robust against adversarial attacks.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). First posted on arXiv 3 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 11; 2022: 6; 2023: 8; 2024: 1; 2025: 1; 2026: 3.

30 papers.

Sort:

By area:

  1. 2022Why So Pessimistic? Estimating Uncertainties for Offline RL through Ensembles, and Why Their Independence Matterscited by 76
  2. 2024Estimating Epistemic and Aleatoric Uncertainty with a Single Modelcited by 54
  3. 2021Posterior Meta-Replay for Continual Learningcited by 45
  4. 2021LiBRe: A Practical Bayesian Approach to Adversarial Detectioncited by 40
  5. 2023HyperDeepONet: learning operator with complex target function space using the limited resources via hypernetworkcited by 26
  6. 2023Principled Weight Initialization for Hypernetworkscited by 19
  7. 2021Bayesian OOD detection with aleatoric uncertainty and outlier exposurecited by 16
  8. 2022Example-based Hypernetworks for Out-of-Distribution Generalizationcited by 16
  9. 2021A Bayesian neural network predicts the dissolution of compact planetary systemscited by 15
  10. 2023Magnitude Invariant Parametrizations Improve Hypernetwork Learningcited by 14
  11. 2021In Defense of the Learning Without Forgetting for Task Incremental Learningcited by 13
  12. 2021Are Bayesian neural networks intrinsically good at out-of-distribution detection?cited by 10
18 more
  1. 2021Safety Enhancement for Deep Reinforcement Learning in Autonomous Separation Assurancecited by 8
  2. 2022Learning Unbiased Transferability for Domain Adaptation by Uncertainty Modelingcited by 8
  3. 2023HyperSINDy: Deep Generative Modeling of Nonlinear Stochastic Governing Equationscited by 8
  4. 2021On out-of-distribution detection with Bayesian neural networkscited by 6
  5. 2023Block-local learning with probabilistic latent representationscited by 6
  6. 2023Implicit Variational Inference for High-Dimensional Posteriorscited by 5
  7. 2021Adversarial Attack for Uncertainty Estimation: Identifying Critical Regions in Neural Networkscited by 4
  8. 2022Time Series Forecasting with Hypernetworks Generating Parameters in Advancecited by 4
  9. 2026Uncertainty-Aware Rank-One MIMO Q Network Framework for Accelerated Offline Reinforcement Learningcited by 3
  10. 2022Distributional Gaussian Processes Layers for Out-of-Distribution Detectioncited by 1
  11. 2025Uncertainty-quantified Rollout Policy Adaptation for Unlabelled Cross-domain Temporal Groundingcited by 1
  12. 2021Generative Particle Variational Inference via Estimation of Functional Gradientscited by 0
  13. 2021Graceful Degradation and Related Fieldscited by 0
  14. 2022Bayesian Neural Network Inference via Implicit Models and the Posterior Predictive Distributioncited by 0
  15. 2023Scale-Space Hypernetworks for Efficient Biomedical Imagingcited by 0
  16. 2023Digital Twin Framework for Optimal and Autonomous Decision-Making in Cyber-Physical Systems: Enhancing Reliability and Adaptability in the Oil and Gas Industrycited by 0
  17. 2026LatentTrack: Sequential Weight Generation via Latent Filteringcited by 0
  18. 2026Learning to Predict Distributions over Weight Updates for Test-Time Adaptationcited by 0