Search Results for author: Matthew M. Graham

Found 6 papers, 5 papers with code

Testing whether a Learning Procedure is Calibrated

no code implementations23 Dec 2020 Jon Cockayne, Matthew M. Graham, Chris J. Oates, T. J. Sullivan

A learning procedure takes as input a dataset and performs inference for the parameters $\theta$ of a model that is assumed to have given rise to the dataset.

Bayesian Inference Statistics Theory Statistics Theory

Measure Transport with Kernel Stein Discrepancy

1 code implementation22 Oct 2020 Matthew A. Fisher, Tui Nolan, Matthew M. Graham, Dennis Prangle, Chris J. Oates

Measure transport underpins several recent algorithms for posterior approximation in the Bayesian context, wherein a transport map is sought to minimise the Kullback--Leibler divergence (KLD) from the posterior to the approximation.

Manifold lifting: scaling MCMC to the vanishing noise regime

1 code implementation9 Mar 2020 Khai Xiang Au, Matthew M. Graham, Alexandre H. Thiery

Standard Markov chain Monte Carlo methods struggle to explore distributions that are concentrated in the neighbourhood of low-dimensional structures.


Manifold Markov chain Monte Carlo methods for Bayesian inference in diffusion models

1 code implementation6 Dec 2019 Matthew M. Graham, Alexandre H. Thiery, Alexandros Beskos

Bayesian inference for nonlinear diffusions, observed at discrete times, is a challenging task that has prompted the development of a number of algorithms, mainly within the computational statistics community.

Computation Methodology 65C40 (Primary) 65C05, 65C40 (Secondary) G.3

Continuously tempered Hamiltonian Monte Carlo

2 code implementations11 Apr 2017 Matthew M. Graham, Amos J. Storkey

Hamiltonian Monte Carlo (HMC) is a powerful Markov chain Monte Carlo (MCMC) method for performing approximate inference in complex probabilistic models of continuous variables.


Asymptotically exact inference in differentiable generative models

1 code implementation25 May 2016 Matthew M. Graham, Amos J. Storkey

We use the intuition that inference corresponds to integrating a density across the manifold corresponding to the set of inputs consistent with the observed outputs.

Cannot find the paper you are looking for? You can Submit a new open access paper.