Ioannis Papageorgiou
Ioannis Papageorgiou is an INFORMED AI Hub Postdoctoral Research Associate based in the School of Mathematics at the University of Bristol, under the supervision of Sid Jaggi. Ioannis obtained his B.A., M.Eng. and Ph.D. in Information and Computer Engineering from the University of Cambridge. His Ph.D. supervisor has been Ioannis Kontoyiannis, and his Ph.D. thesis has been on “Time series modelling and inference with Bayesian Context Trees”.
Research
Ioannis has broad research interests that lie at the interface between Bayesian Statistics, Machine Learning and Information Theory. He is particularly interested in combining modern machine learning techniques with ideas from information theory, which come with strong theoretical foundations and guarantees. His primary focus has been on the modelling and inference of time series (both discrete-valued and real-valued), and more specifically on developing tree-based methods that are inspired by information-theoretic ideas and algorithms. His work has been both methodological, in developing appropriate model classes and algorithms, as well as theoretical, in proving theoretical results that justify the use and guarantee the performance of the methods.
Selected works
-
Bayesian context trees: Modelling and exact inference for discrete time series, accepted at JRSSB (2022).
-
Posterior representations for Bayesian Context Trees: Sampling, estimation and convergence, accepted at Bayesian Analysis (2024).
-
The Bayesian Context Trees State Space Model for time series modelling and forecasting, preprint under revision.
Contact
- Email: tf24342@bristol.ac.uk
- Web: Google Scholar