Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more

DGMs for NLP. A roadmap.

Probabilistic Programming with Gaussian processes in Julia

A curated list of resources about Machine Learning for Robotics

Hashed Lookup Table based Matrix Multiplication (halutmatmul) - Stella Nera accelerator

Implementation of Sequential Attend, Infer, Repeat (SQAIR)

A primer on Bayesian Neural Networks. The aim of this reading list is to facilitate the entry of new researchers into the field of Bayesian Deep Learning, by providing an overview of key papers. More details: "A Primer on Bayesian Neural Networks: Review and Debates"

A Python package for approximate Bayesian inference and optimization using Gaussian processes

Implementations of the ICML 2017 paper (with Yarin Gal)

Input Inference for Control (i2c), a control-as-inference framework for optimal control

PyTorch implementation for "Probabilistic Circuits for Variational Inference in Discrete Graphical Models", NeurIPS 2020

Bayesian optimisation for fast approximate inference in state-space models with intractable likelihoods

Variational Bayesian decision-making for continuous utilities

Benchmark of posterior and model inference algorithms for (moderately) expensive likelihoods.

Approximate Ridge Linear Mixed Models (arLMM)

An implementation of loopy belief propagation for binary image denoising. Both sequential and parallel updates are implemented.

Empirical analysis of recent stochastic gradient methods for approximate inference in Bayesian deep learning, including SWA-Gaussian, MultiSWAG, and deep ensembles. See report_localglobal.pdf.