9 August 2019
Bayesian Nonparametric Statistics
This course covers the fundamentals of Bayesian nonparametric inference and focuses on the key probabilistic concepts and stochastic modelling tools at the basis of recent advances in the field. The outline is the following:
Foundations of Bayesian nonparametric inference: exchangeability, de Finetti's representation theorem
Dirichlet process and clustering
Beyond the Dirichlet process: Pitman-Yor and Gibbs-type processes
Mixture models, Hierarchical models, Covariate-dependent models, Network models
Indian buffet process and feature allocation models
Discovery probabilities: comparing BNP & Good-Turing estimators
Posterior distributions and some elements of Bayesian asymptotics
Lecturer: Dr. Julyan Arbel (Inria Grenoble Rhône-Alpes, France)
Coordinator(s): Matti Vihola & Juha Karvanen
Jyväskylä Summer School offers courses to advanced Master's students, graduate students, and post-docs from the field of Mathematics and Science and Information Technology.
Prerequisites: Basic measure theory, Probability and Statistics.
Learning outcomes: By the end of the course, the students should
have a high-level view of the main approaches to making decisions under uncertainty
be able to detect when being Bayesian helps and why
be able to design and run a Bayesian nonparametric pipeline for standard unsupervised learning
have a global view of the current limitations of Bayesian approaches and the research landscape
be able to understand the abstract of most Bayesian nonparametric papers
EUR 0: Participation in the Summer School courses is free of charge, but students are responsible for covering their own meals, accommodation and travel costs as well as possible visa costs.
Jyväskylä Summer School is not able to grant Summer School students financial support.