TensorFlow Distributions
Joshua V. Dillon, Ian Langmore, Dustin Tran et al. · arXiv (Cornell University) · 2017
The TensorFlow Distributions library implements a vision of probability theory adapted to the modern deep-learning paradigm of end-to-end differentiable computation. Building on two basic abstractions, it offers flexible building blocks for probabilistic computation. Distributions provide fast, numerically stable methods for generating samples and computing statistics, e.g., log density. Bijectors provide composable volume-tracking transformations with automatic caching. Together these enable modular construction of high dimensional distributions and transformations not possible with previous libraries (e.g., pixelCNNs, autoregressive flows, and reversible residual networks). They are the workhorse behind deep probabilistic programming systems like Edward and empower fast black-box inference in probabilistic models built on deep-network components. TensorFlow Distributions has proven an important part of the TensorFlow toolkit within Google and in the broader deep learning community.
Cited by 226 works. doi:10.48550/arxiv.1711.10604 Open-access PDF
Authors
References
- Elements of Information Theory
- An Introduction to the Bootstrap
- GAN(Generative Adversarial Nets)
- R: A Language for Data Analysis and Graphics
- Auto-Encoding Variational Bayes
- A Note on the Generation of Random Normal Deviates
- The NumPy Array: A Structure for Efficient Numerical Computation
- A Comprehensive Introduction to Differential Geometry.
- WaveNet: A Generative Model for Raw Audio
- In-Datacenter Performance Analysis of a Tensor Processing Unit