SMS scnews item created by Hannah Bryant at Fri 24 Feb 2023 1144
Type: Seminar
Modified: Fri 24 Feb 2023 1324; Mon 27 Feb 2023 1244; Mon 27 Feb 2023 1258; Tue 28 Feb 2023 1529; Thu 2 Mar 2023 1252
Distribution: World
Expiry: 2 Mar 2023
Calendar1: 2 Mar 2023 1300-1400
CalLoc1: Quad S249 & Online via Zoom
CalTitle1: SMRI Seminar: Foucart ’Nonstatistical Learning Theory: the View from Optimal Recovery’
Auth: hannahb@10.48.21.5 (hbry8683) in SMS-SAML

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