School of Mathematics, Woodland Road, Bristol BS8 1UG
Tuesday 2nd July 2024
4pm to 5pm
Room 2.04, Fry Building
Colloquium Title: Optimal Recovery as a Worst-Case Learning Theory
This talk showcases the speaker’s recent results in the field of Optimal Recovery, viewed as a trustworthy Learning Theory focusing on the worst case. At the core of several results presented here is a scenario, resolved in the global and the local settings, where the model set is the intersection of two hyperellipsoids. This has implications in optimal recovery from deterministically inaccurate data and in optimal recovery under a multifidelity-inspired model. In both situations, the theory becomes richer when considering the optimal estimation of linear functionals. This particular case also comes with additional results in the presence of randomly inaccurate data.
About the Speaker: Simon Foucart earned a Masters of Engineering from the Ecole Centrale Paris and a Masters of Mathematics from the University of Cambridge in 2001. He received his Ph.D. in Mathematics at the University of Cambridge in 2006, specializing in Approximation Theory. After two postdoctoral positions at Vanderbilt University and University of Paris 6, he joined Drexel University in 2010 before moving to the University of Georgia in 2013. He joined Texas A & M University in 2015 as an associate professor and he is currently a professor of Mathematics. His current work focuses on the modern field of Compressive Sensing, whose theory is exposed in the book ‘A Mathematical Introduction to Compressive Sensing‘ he co-authored with Holger Rauhut.
Simon’s research was recognised by the Journal of Complexity, from which he received the 2010 Best Paper Award. His interests also include the mathematical aspects of metagenomics.
Please register here attend.
For more information please email the Heilbronn events team at heilbronn-coordinator@bristol.ac.uk
Join the Heilbronn Event mailing list to keep up to date with our upcoming events
Comments are closed.