Joint Distributions for TensorFlow Probability
arXiv:2001.11819
Abstract
A central tenet of probabilistic programming is that a model is specified exactly once in a canonical representation which is usable by inference algorithms. We describe JointDistributions, a family of declarative representations of directed graphical models in TensorFlow Probability.
Based on extended abstract submitted to PROBPROG 2020
References in corpus (6)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro
- Importance Weighted Autoencoders
- Variational inference for Monte Carlo objectives
- Effect Handling for Composable Program Transformations in Edward2
Cited by in corpus (5)
- CUQIpy: I. Computational uncertainty quantification for inverse problems in Python
- Probabilistic Deep Learning with Probabilistic Neural Networks and Deep Probabilistic Models
- Automatic structured variational inference
- Embedded-model flows: Combining the inductive biases of model-free deep learning and explicit probabilistic modeling
- PAC-Bayes: Narrowing the Empirical Risk Gap in the Misspecified Bayesian Regime