TensorFlow Probability (JAX backend)

E438358

Python software library open-source software probabilistic programming library statistical modeling library

TensorFlow Probability (JAX backend) is a probabilistic programming and statistical modeling library that runs on JAX, providing tools for Bayesian inference, probabilistic layers, and advanced distributions with XLA-accelerated computation.

Try in SPARQL Jump to: Surface forms Disambiguation Statements Elicitation Referenced by

All labels observed (2)

Label	Occurrences
TensorFlow Probability	5
TensorFlow Probability (JAX backend) canonical	1

How this entity was disambiguated

This entity first appeared as the object of triple T4425385 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: TensorFlow Probability (JAX backend)
Context triple: [JAX, compatibleWith, TensorFlow Probability (JAX backend)]

A. TensorFlow Extended
TensorFlow Extended (TFX) is an end-to-end platform for deploying, managing, and scaling production machine learning pipelines built on TensorFlow.
B. TensorFlow
TensorFlow is an open-source, end-to-end machine learning and deep learning framework widely used for building, training, and deploying neural network models at scale.
C. TensorFlow.js
TensorFlow.js is a JavaScript library that enables training and running machine learning models directly in the browser and in Node.js using TensorFlow.
D. Swift for TensorFlow
Swift for TensorFlow is an experimental machine learning platform that integrates TensorFlow directly into the Swift programming language to enable differentiable programming and high-performance model development.
E. TPUs (via XLA integrations)
TPUs (via XLA integrations) are Google's specialized tensor processing units that can be used as accelerators for PyTorch models through the XLA compilation framework.
F. None of above. chosen
G. Unsure - the case is ambiguous/there is not enough information to decide.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: TensorFlow Probability (JAX backend)
Target entity description: TensorFlow Probability (JAX backend) is a probabilistic programming and statistical modeling library that runs on JAX, providing tools for Bayesian inference, probabilistic layers, and advanced distributions with XLA-accelerated computation.

A. TensorFlow Extended
TensorFlow Extended (TFX) is an end-to-end platform for deploying, managing, and scaling production machine learning pipelines built on TensorFlow.
B. TensorFlow
TensorFlow is an open-source, end-to-end machine learning and deep learning framework widely used for building, training, and deploying neural network models at scale.
C. TensorFlow.js
TensorFlow.js is a JavaScript library that enables training and running machine learning models directly in the browser and in Node.js using TensorFlow.
D. Swift for TensorFlow
Swift for TensorFlow is an experimental machine learning platform that integrates TensorFlow directly into the Swift programming language to enable differentiable programming and high-performance model development.
E. TPUs (via XLA integrations)
TPUs (via XLA integrations) are Google's specialized tensor processing units that can be used as accelerators for PyTorch models through the XLA compilation framework.
F. None of above. chosen

Statements (49)

Predicate	Object
instanceOf	Python software library ⓘ open-source software ⓘ probabilistic programming library ⓘ statistical modeling library ⓘ
basedOn	TensorFlow Probability ⓘ linked to: TensorFlow Probability (JAX backend)
compatibleWith	JAX transformations ⓘ NumPyro-style JAX workflows ⓘ jax.grad ⓘ jax.jit ⓘ jax.pmap ⓘ jax.vmap ⓘ
designedFor	Bayesian modeling ⓘ probabilistic deep learning ⓘ scientific computing ⓘ uncertainty quantification ⓘ
developedBy	Google ⓘ
documentationURL	https://www.tensorflow.org/probability ⓘ
implements	log-probability evaluation ⓘ reparameterization gradients ⓘ sampling from distributions ⓘ transformed distributions via bijectors ⓘ
language	Python ⓘ
license	Apache License 2.0 ⓘ
partOf	TensorFlow ecosystem ⓘ
provides	Monte Carlo estimators ⓘ bijectors ⓘ inference utilities ⓘ probabilistic layers for neural networks ⓘ probability distributions ⓘ random variable abstractions ⓘ tools for Bayesian neural networks ⓘ
supports	Bayesian inference ⓘ GPU acceleration ⓘ Hamiltonian Monte Carlo ⓘ Markov chain Monte Carlo ⓘ No-U-Turn Sampler ⓘ TPU acceleration ⓘ XLA-accelerated computation ⓘ advanced probability distributions ⓘ automatic differentiation ⓘ functional programming style with JAX ⓘ gradient-based optimization ⓘ just-in-time compilation via XLA ⓘ probabilistic layers ⓘ probabilistic programming ⓘ stochastic variational inference ⓘ variational inference ⓘ vectorized probabilistic computation ⓘ
usesBackend	JAX ⓘ

How these facts were elicited