The main aim of this workshop is to allow leading Bayesian researchers in machine learning to get together presenting their latest ideas and discussing future directions. The workshop will provide a forum to discuss Bayesian inference in machine learning. A particular focus will be on how Bayesian inference can be used to encode prior knowledge.
- Incorporating Complex Prior Knowledge in Bayesian inference, for example mechanistic models (such as differential equations) or knowledge transfered from other related situations (e.g. hierarchical Dirichlet Processes).
- Model mismatch: the Bayesian lynch pin is that the model is correct, but it rarely is.
- Approximation techniques: how should we do Bayesian inference in practice. Sampling, variational, Laplace or something else?
- Your pet Bayesian issue here.