-
Sequential Neural Posterior and Likelihood Approximation
A paper on simulation-based inference where we present an algorithm that learns both the posterior and the likelihood of the model.
-
In this paper, we use correlated particle pseudo-marginal Metropolis-Hastings (CPMMH) for accelerating inference for stochastic differential equation mixed-effects models (SDEMEMs).
-
A deep learning paper where we introduce the novel architecture partially exchangeable networks (PEN). In the paper, we use PEN for learning summary statistics for ABC.
-
Accelerating delayed-acceptance Markov chain Monte Carlo algorithms
An MCMC paper where we develop an accelerated version of the delayed-acceptance algorithm. As a case study, we consider the computational challenging and highly complex problem of modeling protein folding.
-
Implementation of some ABC algorithms in Julia
Generic implementations of some ABC algorithms in Julia.
-
Introduction to likelihood-free inference
An introductory Jupyter notebook tutorial on likelihood-free inference.
-
Pioneers-pp: Bayesian statistics and ABC talk
Slides, examples, and computer exercises for my presentation at the Pioneers of Probabilistic Programming Meet-up group.
-
Slides for my talk at Bayes@Lund 2019.
-
A list of some useful terminal/git commands that I regularly use.