Stein Point Markov Chain Monte Carlo

9 May 20191 code implementation

Stein Points are a class of algorithms for this task, which proceed by sequentially minimising a Stein discrepancy between the empirical measure and the target and, hence, require the solution of a non-convex optimisation problem to obtain each new point.

BAYESIAN INFERENCE

Pseudo-extended Markov chain Monte Carlo

NeurIPS 2019 1 code implementation

In this paper, we introduce the pseudo-extended MCMC method as a simple approach for improving the mixing of the MCMC sampler for multi-modal posterior distributions.

sgmcmc: An R Package for Stochastic Gradient Markov Chain Monte Carlo

2 Oct 20171 code implementation

To do this, the package uses the software library TensorFlow, which has a variety of statistical distributions and mathematical operations as standard, meaning a wide class of models can be built using this framework.

BAYESIAN INFERENCE

Gradient-based Adaptive Markov Chain Monte Carlo

NeurIPS 2019 1 code implementation

We introduce a gradient-based learning method to automatically adapt Markov chain Monte Carlo (MCMC) proposal distributions to intractable targets.

Improving Sampling from Generative Autoencoders with Markov Chains

28 Oct 20161 code implementation

Generative autoencoders are those which are trained to softly enforce a prior on the latent distribution learned by the inference model.

Generalizing Hamiltonian Monte Carlo with Neural Networks

ICLR 2018 2 code implementations

We present a general-purpose method to train Markov chain Monte Carlo kernels, parameterized by deep neural networks, that converge and mix quickly to their target distribution.

A-NICE-MC: Adversarial Training for MCMC

NeurIPS 2017 2 code implementations

We propose A-NICE-MC, a novel method to train flexible parametric Markov chain kernels to produce samples with desired properties.

Metropolis-Hastings Generative Adversarial Networks

28 Nov 20183 code implementations

We introduce the Metropolis-Hastings generative adversarial network (MH-GAN), which combines aspects of Markov chain Monte Carlo and GANs.

Approximate Inference for Constructing Astronomical Catalogs from Images

28 Feb 20181 code implementation

We present a new, fully generative model for constructing astronomical catalogs from optical telescope image sets.

Holistic 3D Scene Parsing and Reconstruction from a Single RGB Image

ECCV 2018 1 code implementation

We propose a computational framework to jointly parse a single RGB image and reconstruct a holistic 3D configuration composed by a set of CAD models using a stochastic grammar model.

3D OBJECT DETECTION OBJECT LOCALIZATION SCENE UNDERSTANDING SEMANTIC SEGMENTATION