A | Foundations of Machine Learning


A1 | Statistical Foundations & Explainability

Research is being conducted at MCML to improve the reliability, interpretability, and acceptability of results obtained with ML algorithms for their practical application through better integration of statistical concepts. Key challenges include the integration of uncertainty quantification into ML algorithms, the explainability of ML models, the simplification of ML methods, and the incorporation of prior knowledge into ML algorithms.

Link to Bernd Bischl

Prof. Dr. Bernd Bischl

LMU München

Statistical Learning & Data Science

Link to Anne-Laure Boulesteix

Prof. Dr. Anne-Laure Boulesteix

LMU München

Biometry in Molecular Medicine

Link to Mathias Drton

Prof. Dr. Mathias Drton

TU München

Mathematical Statistics

Link to Matthias Feurer

Prof. Dr. Matthias Feurer

LMU München

Statistical Learning & Data Science

Link to Göran Kauermann

Prof. Dr. Göran Kauermann

LMU München

Applied Statistics in Social Sciences, Economics and Business

Link to Thomas Nagler

Prof. Dr. Thomas Nagler

LMU München

Computational Statistics & Data Science

Link to David Rügamer

Prof. Dr. David Rügamer

LMU München

Data Science Group

Link to Fabian Scheipl

PD Dr. Fabian Scheipl

LMU München

Functional Data Analysis

Link to Volker Schmid

Prof. Dr. Volker Schmid

LMU München

Bayesian Imaging & Spatial Statistics

A2 | Mathematical Foundations

Some of the tremendous successes of ML have been achieved through the use of mathematical insights. The contribution of our mathematicians in MCML can be divided into two main research areas: Mathematics for ML, i.e., mathematical principles are used to develop new reliable ML algorithms, and ML mathematics, i.e. ML is used to advance mathematical research, e.g. in imaging, inverse problems, optimal control, or numerical analysis of partial differential equations.

Link to Ulrich Bauer

Prof. Dr. Ulrich Bauer

TU München

Applied Topology and Geometry

Link to Massimo Fornasier

Prof. Dr. Massimo Fornasier

TU München

Applied Numerical Analysis

Link to Reinhard Heckel

Prof. Dr. Reinhard Heckel

TU München

Machine Learning

Link to Felix Krahmer

Prof. Dr. Felix Krahmer

TU München

Optimization & Data Analysis

Link to Gitta Kutyniok

Prof. Dr. Gitta Kutyniok

LMU München

Mathematical Foundations of Artificial Intelligence

A3 | Computational Models

Mathematical models and statistical concepts, which are core elements of ML methods, must be reflected by efficient algorithmic implementations. Furthermore, the execution of corresponding algorithms requires a suitable computational infrastructure. Currently, the steady growth of ML applications brings new algorithmic problems and computational challenges that MCML is addressing in this research area. This includes the scalability of large data sets and data streams, the adaptations of ML algorithms to modern hardware and computational infrastructures, and the exploration of methods for Constrained ML, Informed ML, Learning with Multi­relational Data such as Knowledge-Graphs, and AutoML.

Link to Stephan Günnemann

Prof. Dr. Stephan Günnemann

TU München

Data Analytics & Machine Learning

Link to Eyke Hüllermeier

Prof. Dr. Eyke Hüllermeier

LMU München

Artificial Intelligence & Machine Learning

Link to Niki Kilbertus

Prof. Dr. Niki Kilbertus

TU München

Ethics in Systems Design and Machine Learning

Link to Matthias Schubert

Prof. Dr. Matthias Schubert

LMU München

Database Systems & Data Mining

Link to Thomas Seidl

Prof. Dr. Thomas Seidl

LMU München

Database Systems & Data Mining

Link to Volker Tresp

Prof. Dr. Volker Tresp

LMU München

Database Systems & Data Mining