mlsanityData to 14 Oct 2026

Bayesian Hypernetworks

arXiv 1710.04759 ↗First posted 13 Oct 2017stat.ML cs.AI cs.LGcited by 66

Not on the map. Why?

Abstract (arXiv)

We study Bayesian hypernetworks: a framework for approximate Bayesian inference in neural networks. A Bayesian hypernetwork h is a neural network which learns to transform a simple noise distribution, p(vecε) = N(vec 0,mat I), to a distribution q(pp) := q(h(vecε)) over the parameters pp of another neural network (the "primary network")@. We train q with variational inference, using an invertible h to enable efficient estimation of the variational lower bound on the posterior p(pp | D) via sampling. In contrast to most methods for Bayesian deep learning, Bayesian hypernets can represent a complex multimodal approximate posterior with correlations between parameters, while enabling cheap iid sampling of~q(pp). In practice, Bayesian hypernets can provide a better defense against adversarial examples than dropout, and also exhibit competitive performance on a suite of tasks which evaluate model uncertainty, including regularization, active learning, and anomaly detection.

Key facts. Cited by 66 papers in the map (data through 14 Oct 2026). First posted on arXiv 13 Oct 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 11; 2023: 14; 2024: 8; 2025: 7; 2026: 14.

66 papers.

Sort:

By area:

  1. 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
  2. 2021Editing Factual Knowledge in Language Modelscited by 553
  3. 2023A Brief Review of Hypernetworks in Deep Learningcited by 102
  4. 2021Priors in Bayesian Deep Learning: A Reviewcited by 101
  5. 2023Permutation Equivariant Neural Functionalscited by 70
  6. 2023Massive Editing for Large Language Models via Meta Learningcited by 63
  7. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 62
  8. 2024Estimating Epistemic and Aleatoric Uncertainty with a Single Modelcited by 54
  9. 2023Neural Functional Transformerscited by 52
  10. 2021Posterior Meta-Replay for Continual Learningcited by 45
  11. 2021Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equationscited by 38
  12. 2022Learning the Effect of Registration Hyperparameters with HyperMorphcited by 35
38 more
  1. 2024Universal Neural Functionalscited by 26
  2. 2023FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregationcited by 22
  3. 2024HyperFast: Instant Classification for Tabular Datacited by 22
  4. 2022Hypernetworks for Zero-shot Transfer in Reinforcement Learningcited by 19
  5. 2023Principled Weight Initialization for Hypernetworkscited by 19
  6. 2022Example-based Hypernetworks for Out-of-Distribution Generalizationcited by 16
  7. 2022Boosting Natural Language Generation from Instructions with Meta-Learningcited by 15
  8. 2025Amortized In-Context Bayesian Posterior Estimationcited by 15
  9. 2023Magnitude Invariant Parametrizations Improve Hypernetwork Learningcited by 14
  10. 2024Credal Wrapper of Model Averaging for Uncertainty Estimation in Classificationcited by 13
  11. 2023When Meta-Learning Meets Online and Continual Learning: A Surveycited by 12
  12. 2021Are Bayesian neural networks intrinsically good at out-of-distribution detection?cited by 10
  13. 2021Regularization-Agnostic Compressed Sensing MRI Reconstruction with Hypernetworkscited by 9
  14. 2022Meta-Learning via Classifier(-free) Diffusion Guidancecited by 9
  15. 2022Computing Multiple Image Reconstructions with a Single Hypernetworkcited by 8
  16. 2021Multi-Task Neural Processescited by 7
  17. 2023Generative Hyperelasticity with Physics-Informed Probabilistic Diffusion Fieldscited by 7
  18. 2026Learning Credal Ensembles via Distributionally Robust Optimizationcited by 7
  19. 2021On out-of-distribution detection with Bayesian neural networkscited by 6
  20. 2023Implicit Variational Inference for High-Dimensional Posteriorscited by 5
  21. 2022Time Series Forecasting with Hypernetworks Generating Parameters in Advancecited by 4
  22. 2023Exploring the Approximation Capabilities of Multiplicative Neural Networks for Smooth Functionscited by 4
  23. 2022Learning the Space of Deep Modelscited by 3
  24. 2022Deep representation learning: Fundamentals, Perspectives, Applications, and Open Challengescited by 3
  25. 2025Uncertainty quantification of neural network models of evolving processes via Langevin samplingcited by 2
  26. 2025CLAPS: Aleatoric-Epistemic Scaling via Last-Layer Laplace for Conformal Regressioncited by 2
  27. 2021Object Pursuit: Building a Space of Objects via Discriminative Weight Generationcited by 1
  28. 2022Meta-Learning over Time for Destination Prediction Taskscited by 1
  29. 2023Efficient Verification-Based Face Identificationcited by 1
  30. 2024Recall-Oriented Continual Learning with Generative Adversarial Meta-Modelcited by 1
  31. 2025GenUQ: Predictive Uncertainty Estimates via Generative Hyper-Networkscited by 1
  32. 2025Generative AI Meets 6G and Beyond: Diffusion Models for Semantic Communicationscited by 1
  33. 2025Maxitive Donsker-Varadhan Formulation for Possibilistic Variational Inferencecited by 1
  34. 2026Set-based v.s. Distribution-based Representations of Epistemic Uncertainty: A Comparative Studycited by 1
  35. 2026Hyper-V2X: Hypernetworks for Estimating Epistemic and Aleatoric Uncertainty in Cooperative Bird's-Eye-View Semantic Segmentationcited by 1
  36. 2021Generative Particle Variational Inference via Estimation of Functional Gradientscited by 0
  37. 2021Challenges and Opportunities in Approximate Bayesian Deep Learning for Intelligent IoT Systemscited by 0
  38. 2022Bayesian Neural Network Inference via Implicit Models and the Posterior Predictive Distributioncited by 0

50 most cited of 66 All 66 (JSON)