SMRI Seminar: Foucart -- Nonstatistical Learning Theory: the View from Optimal Recovery

SMRI Seminar: 
'Nonstatistical Learning Theory: the View from Optimal Recovery' 
Simon Foucart (Texas A&M University) 

Thursday 2nd March 1:00-2:00 PM Quad S249 & online via Zoom 
(Join: https://uni-sydney.zoom.us/j/89421015266) 

Abstract: For a function observed through point evaluations, is there an optimal way to
recover it or merely to estimate a dependent quantity? I will give affirmative answers
to variations of this data-focused question, especially under the assumption that the
function belongs to a model set defined by approximation capabilities.  In fact, I will
uncover computationally implementable linear recovery maps that are optimal in the
worst-case setting.  I will present some recent and ongoing works extending the theory
in several directions, with particular emphasis put on observations that are
inexact---adversarially or randomly.  

Please note that this seminar will not be recorded.  

---- 

Join us afterwards on the SMRI Terrace for afternoon tea (2:00-2:45pm, weekly).  

---- 

Upcoming SMRI events can be found here:
https://mathematical-research-institute.sydney.edu.au/news-events/ 

SMRI YouTube Channel: https://www.youtube.com/c/SydneyMathematicalResearchInstituteSMRI