We are glad to inform you that the next Applied Bayesian Statistics school - ABS24 will be held in the city of Como (Italy), along the Lake Como shoreline, on August 26-30, 2024.
The school is organized by CNR IMATI (Institute for Applied Mathematics and Information Technologies at the National Research Council of Italy in Milano), in cooperation with Fondazione Alessandro Volta.
The topic will be BAYESIAN PHYLOGENETICS AND INFECTIOUS DISEASES.
The lecturer will be Prof. MARC SUCHARD (Department of Biostatistics, UCLA Fielding School of Public Health, USA), with the support of Filippo Monti (PhD student in Biostatistics, UCLA, USA).
As in the past (since 2004), there will be a combination of theoretical and practical sessions, along with presentations by participants about their work (past, current and future) related to the topic of the school.
OUTLINE: The aim of this course is to explore the core challenges of Bayesian inference of stochastic processes in modern biology in terms of data-scale, model-dimensionality and compute-complexity. Challenging and
emerging statistical solutions will be illustrated through the analysis of biological sequences, such as genes and genomes. Molecular phylogenetics has become an essential analytical tool for understanding the complex patterns in which rapidly evolving pathogens propagate across and between countries, owing to the complex travel and transportation patterns evinced by modern economies, along with growing political factors such as increased global population and urbanization.
As an accessible course for all, a brief introduction of the underlying biology (for statistical researchers) and of modern Bayesian inference (for practicing biologists) will be also provided.
Topics will cover probabilistic modeling techniques using both discrete- and continuous-valued stochastic processes including continuous-time Markov chains and Gaussian processes; large-scale data-integration approaches incorporating factors like human mobility and climate measurements; recursive computing and other mathematical tricks to evaluate seemingly intractable likelihoods; state-of-the-art sampling methods for high-dimensional models including Hamiltonian Monte Carlo and its more recent non-reversible extensions; delivering timely inference on advancing computing hardware like graphics processing units and (maybe even) quantum devices.