This page maintains a collection of papers/resources in different categories related to Bayesian Deep Learning & Deep Bayesian Learning (see YW Teh’s talk on the dichotomy). (last updated: 2018/8)

Some books

Core

A generic formula for models with latent variables:

  • PGM Chapter 19

Markov Chain Monte Carlo (MCMC) theory and classic algorithms:

  • PGM Chapter 12
  • PRML Chapter 11

Hamiltonian Monte Carlo (HMC):

Expectation Maximization (EM) and Variational Inference (VI):

Amortized Variational Inference and Reparameterization Trick:

Hierarchical Variational Methods:

Variance Reduction in VI:

Expectation Propagation (EP):

Deep State Space Models

Normalizing Flows

Importance Weighted Autoencoder

Implicit Inference

Transfer Learning and Semisupervised Learning

Representation Learning

Disentanglement in Deep Representations

Memory Addressing, Localization and Inference

Discrete Latent Variable

Bayesian Deep Neural Networks (Variational Approaches)

Bayesian Compression

Bayesian Deep Neural Networks (MCMC Approaches)

Deep neural networks = Gaussian Process

SGD / Approximate Inference / PAC-Bayes