ZhuSuan: A Library for Bayesian Deep Learning
arXiv:1709.05870
Abstract
In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning. ZhuSuan is built upon Tensorflow. Unlike existing deep learning libraries, which are mainly designed for deterministic neural networks and supervised tasks, ZhuSuan is featured for its deep root into Bayesian inference, thus supporting various kinds of probabilistic models, including both the traditional hierarchical Bayesian models and recent deep generative models. We use running examples to illustrate the probabilistic programming on ZhuSuan, including Bayesian logistic regression, variational auto-encoders, deep sigmoid belief networks and Bayesian recurrent neural networks.
The GitHub page is at https://github.com/thu-ml/zhusuan
References in corpus (15)
- TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems
- Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
- End to End Learning for Self-Driving Cars
- Improved Techniques for Training GANs
- A Conceptual Introduction to Hamiltonian Monte Carlo
- Markov Chain Monte Carlo and Variational Inference: Bridging the Gap
- Edward: A library for probabilistic modeling, inference, and criticism
- Composing graphical models with neural networks for structured representations and fast inference
- Variational inference for Monte Carlo objectives
- Inference Networks for Sequential Monte Carlo in Graphical Models
- Neural Adaptive Sequential Monte Carlo
- Reweighted Wake-Sleep
- Approximate Inference with Amortised MCMC
- Learning Model Reparametrizations: Implicit Variational Inference by Fitting MCMC distributions
- Towards Robust Detection of Adversarial Examples
Cited by in corpus (16)
- TensorFlow Distributions
- A Factor Graph Approach to Automated Design of Bayesian Signal Processing Algorithms
- A Spectral Approach to Gradient Estimation for Implicit Distributions
- Simple, Distributed, and Accelerated Probabilistic Programming
- Quantum Capsule Networks
- Amortized Variational Inference: A Systematic Review
- Advances in Variational Inference
- Pre-Trained Models: Past, Present and Future
- Variational Implicit Processes
- Semi-crowdsourced Clustering with Deep Generative Models
- Ivy: Templated Deep Learning for Inter-Framework Portability
- Kernel Implicit Variational Inference
- Scalable Training of Inference Networks for Gaussian-Process Models
- Efficient Computation Reduction in Bayesian Neural Networks Through Feature Decomposition and Memorization
- Coupled Variational Recurrent Collaborative Filtering
- Critical Temperature Prediction for a Superconductor: A Variational Bayesian Neural Network Approach