mlsanityData to 7 Oct 2026

TyXe: Pyro-based Bayesian neural nets for Pytorch

arXiv 2110.00276 ↗First posted 1 Oct 2021stat.ML cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

We introduce TyXe, a Bayesian neural network library built on top of Pytorch and Pyro. Our leading design principle is to cleanly separate architecture, prior, inference and likelihood specification, allowing for a flexible workflow where users can quickly iterate over combinations of these components. In contrast to existing packages TyXe does not implement any layer classes, and instead relies on architectures defined in generic Pytorch code. TyXe then provides modular choices for canonical priors, variational guides, inference techniques, and layer selections for a Bayesian treatment of the specified architecture. Sampling tricks for variance reduction, such as local reparameterization or flipout, are implemented as effect handlers, which can be applied independently of other specifications. We showcase the ease of use of TyXe to explore Bayesian versions of popular models from various libraries: toy regression with a pure Pytorch neural network; large-scale image classification with torchvision ResNets; graph neural networks based on DGL; and Neural Radiance Fields built on top of Pytorch3D. Finally, we provide convenient abstractions for variational continual learning. In all cases the change from a deterministic to a Bayesian neural network comes with minimal modifications to existing code, offering a broad range of researchers and practitioners alike practical access to uncertainty estimation techniques. The library is available at https://github.com/TyXe-BDL/TyXe.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 26 of its 53 references that are in the map. First posted on arXiv 1 Oct 2021.

Builds on

26 of 53 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,416
  4. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  5. 2015Variational Dropout and the Local Reparameterization Trickcited by 489
  6. 2018Pyro: Deep Universal Probabilistic Programmingcited by 379
  7. 2017Variational Continual Learningcited by 335
  8. 2013Black Box Variational Inferencecited by 317
  9. 2015Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networkscited by 295
  10. 2017Multiplicative Normalizing Flows for Variational Bayesian Neural Networkscited by 157
  11. 2018Flipout: Efficient Pseudo-Independent Weight Perturbations on Mini-Batchescited by 133
  12. 2018Bayesian graph convolutional neural networks for semi-supervised classificationcited by 88
14 more
  1. 2016Structured and Efficient Variational Deep Learning with Matrix Gaussian Posteriorscited by 82
  2. 2020Bayesian Graph Neural Networks with Adaptive Connection Samplingcited by 81
  3. 2018Bayesian Layers: A Module for Neural Network Uncertaintycited by 57
  4. 2013Automated Variational Inference in Probabilistic Programmingcited by 31
  5. 2017Learning Discrete Weights Using the Local Reparameterization Trickcited by 29
  6. 2021Uncertainty Quantification 360: A Holistic Toolkit for Quantifying and Communicating the Uncertainty of AIcited by 22
  7. 2018Overpruning in Variational Bayesian Neural Networkscited by 21
  8. 2021BNNpriors: A library for Bayesian neural network inference with different prior distributionscited by 20
  9. 2018Simple, Distributed, and Accelerated Probabilistic Programmingcited by 18
  10. 2021Sparse Uncertainty Representation in Deep Learning with Inducing Weightscited by 16
  11. 2019Improving and Understanding Variational Continual Learningcited by 12
  12. 2019Learning from the Past: Continual Meta-Learning via Bayesian Graph Modelingcited by 9
  13. 2020Bayesian Graph Neural Networks for Molecular Property Predictioncited by 8
  14. 2018Probabilistic Meta-Representations Of Neural Networkscited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 2; 2024: 1; 2025: 0; 2026: 1.

6 papers.

  1. 2024Position: Bayesian Deep Learning is Needed in the Age of Large-Scale AIcited by 60
  2. 2023Fortuna: A Library for Uncertainty Quantification in Deep Learningcited by 14
  3. 2023A Benchmark on Uncertainty Quantification for Deep Learning Prognosticscited by 9
  4. 2022Black-box Coreset Variational Inferencecited by 4
  5. 2022Density Regression and Uncertainty Quantification with Bayesian Deep Noise Neural Networkscited by 1
  6. 2026Neetyabhas: A Framework for Uncertainty-Aware Public Policy Optimization in Rational Agent-Based Modelscited by 0