The course will consist of 10 hours, 2h per day. The outline is the following:
1. Markov Processes; Markov Chain Monte Carlo; Hybrid (a.k.a. Hamilton) Monte Carlo.
2. Fundamentals of Bayesian Inference. Laplace Approximation
3. Variational Inference; Kullback-Leibler divergence. Working example with Tensorflow v2 (python)
4. Inference in function space: Gaussian Processes, Implicit Processes.
5. Approximate Bayesian Computation (ABC). Likelihood-free method. Normalizing flows.
Many of the topics will be accompanied by coding examples.
****** DAY, TIME, ROOM, SPEAKER ***
- Monday, 11:00 - 13:00. 1001-Primera-1-1-1 - Paterna. Seminario. Alberto Ramos
- Tuesday, 9:30 - 11:30. 1001-Primera-1-1-1 - Paterna. Seminario. Bryan Zaldivar
- Wednesday, 11:00 - 13:00. 1001-Primera-1-1-1 - Paterna. Seminario. Bryan Zaldivar
- Thursday, 09:30 - 11:30. 1001-Primera-1-1-1 - Paterna. Seminario. Bryan Zaldivar
- Friday, 14:30 - 16:30. 1001-Primera-1-1-1 - Paterna. Seminario. Bryan Zaldivar