Centrum Wiskunde & Informatica (CWI) has vacancies in the Machine Learning research group for two enthusiastic talented
Postdocs (m/v/x) within
Peter Grünwald’s ERC Advanced Grant Project FLEX (FLEXible Statistical Inference).
Job description Most statistical methods require that all aspects of data collection and inference are determined in advance, independently of the data. These include when to stop collecting data, what decisions can be made (i.e. accept/reject null hypothesis), and how to measure their quality (e.g. loss function/significance level). This is
wildly at odds with the flexibility required in practice! It is a leading cause of the
replicability crisis in the applied sciences.
The project aims to develop novel theory and methods of statistics in which all data-collection and decision-aspects may be unknown in advance, possibly imposed post-hoc. Yet the new theory will provide valid small-sample error control and uncertainty quantification. The theory will be based on far-reaching extensions of
e-values,
e-processes, and the
e-
posterior, flexible alternatives for p-values and Bayes factors that have been developed over the last five years. Other key topics include
anytime-valid confidence sequences, concentration inequalities, martingales and
the foundations of statistics (likelihood principle, complete class theorems).
The vacancies are for two three-year postdocs to do research within the FLEX project.