Mathematics of Data


Tuesday, Aug 14th, 2018, 16:30
Afonso Bandeira (Courant Institute of Mathematical Sciences, New York)
Statistical estimation under group actions: The Sample Complexity of Multi-Reference Alignment
MPI MIS Leipzig, room E1 05 (Leibniz-Saal)

Wednesday, Jul 11th, 2018, 15:30
Harald Oberhauser (University of Oxford)
Learning laws of stochastic processes
MPI MIS Leipzig, room E1 05 (Leibniz-Saal)

Monday, Jun 18th, 2018, 15:30
Anna Seigal (University of California, Berkeley)
Structured Tensors and the Geometry of Data
MPI MIS Leipzig, room G3 10 (Hörsaal)

Wednesday, May 2nd, 2018, 11:00
Steffen Lauritzen (University of Copenhagen, Denmark)
Max-linear Bayesian networks
MPI MIS Leipzig, room E1 05 (Leibniz-Saal)

Tuesday, Apr 24th, 2018, 15:30
Benjamin Recht (University of California, Berkeley)
The statistical foundations of learning to control
MPI MIS Leipzig, room E1 05 (Leibniz-Saal)

Summer term 2018
André Uschmajew
Low-rank tensor approximation
MPI MIS Leipzig, room G3 10, Thursday 11:00

Summer term 2018
Jürgen Jost
Geometric and topological methods in data analysis
MPI MIS Leipzig, room A3 01, Friday 13:30

Summer term 2018 - Weekend Course
Bernd Sturmfels
Introduction to Algebraic Statistics
TU Berlin / Harnack-Haus, May 25 - 27, whole day

Winter term 2018/19
Nihat Ay
Machine Learning

August 13 - 17, 2018
Summer School on Numerical Computing in Algebraic Geometry
Organiser: M. Kummer, P. Breiding, Y. Ren, E. Sertöz
MPI MIS Leipzig, room E1 05 (Leibniz-Saal)

Autumn 2018
Deep Learning Theory
(Kick-Off-Meeting of ERC Starting Grant Project)
Organiser: Guido Montúfar

April 1 - 5, 2019
Low-rank Optimization and Applications
Organiser: André Uschmajew
MPI MIS Leipzig, room E1 05 (Leibniz-Saal)


 Initiators Nihat Ay, Christiane Görgen, Guido Montúfar, André Uschmajew 
 Aim Data, in its many forms and across various disciplines, is becoming an essential source for research in the 21st century. In fact, data driven knowledge extraction nowadays constitutes one of the core paradigms for scientific discovery. Therefore, the development of efficient techniques for the integration of large data sets is more necessary than ever. Mathematics offers efficient methodologies from its various well-developed subfields for achieving this goal. Recognising the broad scientific expertise at the Max Planck Institute for Mathematics in the Sciences within the scope of data science, our initiative aims at bundling the corresponding efforts and activities in order to consolidate and advance research on Mathematics of Data.  
 Participating Groups Information Theory of Cognitive Systems
Nihat Ay

Algebraic Statistics
Christiane Görgen

Geometry and Complex Systems
Jürgen Jost

Deep Learning Theory
Guido Montúfar

Opinion dynamics and cultural Conflict in European Spaces
Eckehard Olbrich

Structure of Evolution
Matteo Smerlak

Bioinformatics (Leipzig University)
Peter F. Stadler

Nonlinear Algebra
Bernd Sturmfels

Tensors and Optimization
André Uschmajew