ERC Advanced Grant for Mathias Drton

Funding of Project GRAPHMODE

15 April 2020
Mathias Drton

Mathias Drton, TUM Professor of Mathematical Statistics, receives one of the prestigious Advanced Grants from the European Research Council (ERC) for his project "Graphical Models for Complex Multivariate Data". It is the first Advanced Grant at our Department - after 4 ERC Starting Grants and 2 ERC Consolidator Grants so far.

The ERC Advanced Grants

Professor Mathias Drton is one of 185 winners of the annual ERC Advanced Grants competition. The grant supports the most innovative research projects of excellent scientists who have a track-record of significant achievements in the last ten years.

The ERC Advanced Grants may be awarded up to 2.5 million euros for a period of 5 years and are designed to strengthen Europe's knowledge base. Amongst other things, they support new positions for postdocs, doctoral students and other researchers.

The funding is part of the Horizont 2020 research and innovation program and the winners will carry out research at universities and research centers in 20 EU Member States and associated countries. Germany (35), the United Kingdom (34) and France (21) receive the most grants.

The project GRAPHMODE

Modern scientific experiments frequently produce multivariate data on the activity of the components of complex systems. In his project "Graphical Models for Complex Multivariate Data" (GRAPHMODE), Mathias Drton develops new theory and methods for statistical analysis of such data. The considered graphical models are probabilistic models that are able to capture detailed causal dependencies between the components of a system.

Applications of graphical models, e.g., in patient studies in medicine or in gene expression studies in biology, often face important challenges such as key variables being latent (i.e., unobservable or unobserved), lacking temporal resolution in studies of feedback loops, and limited experimental interventions. The aim of the project GRAPHMODE is to obtain a deeper understanding of the inherent limitations on what can be inferred from imperfect measurements, and to design novel statistical methodology to infer estimable quantities. 

Essential
These cookies are technically necessary.
Details >Details ausblenden
Statistics
These cookies help us to analyse user behavior and thus to improve your experience on our website.
Details >Details ausblenden