Old recordings

Below is a list of recordings of 2023 lectures for MVE187/MSA102 Computational Methods for Bayesian statistics. 

NOTE: There is no guarantee that the contents of the 2024 course will be exactly the same as that of the 2023 course. However, they should be roughly similar.

Lecture 1: Introduction to the Bayesian paradigm. Issues with classical frequentist inference. Links to an external site.

Lecture 2: Basic computations using conjugacy. The exponential family of distributions. Links to an external site.

Lecture 3: Using discretization. Mixtures. Some multivariate conjugacies. Links to an external site.

Lecture 4: Inference by simulation. Monte Carlo integration. Basic simulation methods. Rejection sampling. More about priors. Links to an external site.

Lecture 5: Importance sampling and SIR. The multivariate Normal and Laplace approximation. Introduction to Markov chain Monte Carlo (MCMC) methods. Links to an external site.

Lecture 6: MCMC. Random walk. Independent proposal. Convergence; checking convergence. Burn-in. Smart proposals. Links to an external site.

Lecture 7: Hierarchical models. Tips and tricks. Convergence. Links to an external site.

Lecture 8: Hierarchical models. Gibbs sampling. Missing data / augmented data. Links to an external site.

Lecture 9. Hamiltonian MCMC. State space models. Hidden Markov Models. Kalman Links to an external site.

Lecture 10: Kalman filters. Particle filters. Links to an external site.

Lecture 11: Some information theory. The EM algorithm. Links to an external site.

Lecture 12: Parameter inference in state space models. Links to an external site.

Lecture 13: Variational Bayes. A sampling example (slice sampling). Links to an external site.

Lecture 14: Graphical Models. Links to an external site.

Lecture 15: Finishing graphical models. Applied Bayesian modelling. Links to an external site.

Review Links to an external site.