May 23 - 27, 2022

Lipschitz Lecture Hall, Mathematics Center, Endenicher Allee 60

Organizers: Anne Driemel, Melanie Schmidt

Description: In this Hausdorff School we study algorithmic aspects of foundational methods to learn and generalise from data. While the nexus is algorithmic, this area of research is a rich and vibrant field within theoretical computer science which draws from deep connections to statistics, geometry, and combinatorics.

This Hausdorff School is intended for motivated graduate or postdoctoral students of mathematics or computer science. Leading experts discuss geometric and probabilistic approximation techniques and their connections to learning theory. Each invited speaker gives a mini-course spanning three lectures ranging from introductory material to advanced topics and current research.

Lecture Series by:

• Ken Clarkson (IBM Research, US)
• Matrix sketching techniques for data analysis
• Ioannis Emiris (Athena Research Center and U. Athens, Greece)
• Geometric approximation in general dimension
• Robert Krauthgamer (Weizmann Institute, Israel)
• Streaming algorithms for vectors and matrices
• David Mount (University of Maryland, US)
• Analysis of spatial data from the perspective of proximity
• Jeff Phillips (University of Utah, US)
• Sketching geometric data for simple machine learning on complex data
• Ruth Urner (York University, Canada)
• Statistical learning theory

Please see the schedule here.

The deadline for applications was March 27, 2022.

In case of questions, please contact the organizers at hsm-him(at)him.uni-bonn.de