BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Machine Learning on Non-Euclidean Domains: Powersets\, Lattices\, 
 Posets
DTSTART:20230428T101500
DTEND:20230428T111500
DTSTAMP:20260408T035044Z
UID:573d0baaf9ef608e8f204ff9a06708ecbff03216c65efa85e316d6a0
CATEGORIES:Conferences - Seminars
DESCRIPTION:Chris Wendler \nIn this presentation\, Chris will discuss the 
 key findings from his Ph.D. research on Fourier-sparse learning on powerse
 ts\, lattices\, and partially ordered sets (posets). His research builds u
 pon and expands the recent signal processing theory for set functions\, wh
 ich is an instantiation of algebraic signal processing theory (ASP) to the
  powerset domain.\n\nASP offers a theoretical framework for the axiomatic 
 derivation of signal processing operations such as convolutional filters a
 nd Fourier transforms from appropriate shift operations that capture the c
 haracteristics of a specific domain. When applied to the powerset domain\,
  ASP gives rise to four novel non-orthogonal Fourier transforms. Chris has
  developed sparse Fourier transform algorithms for these novel bases\, sub
 stantially expanding the family of learnable set functions. The resulting 
 Fourier-sparse representations are particularly well-suited for combinator
 ial auctions\, where bidders place bids on subsets of goods\, and their pr
 eferences are modelled using set functions. Inspired by this observation\,
  we designed an auction mechanism that utilizes Fourier-sparse bidder repr
 esentations.\n\nChris Wendler earned his B.Sc. in Mathematics and M.Sc. in
  Computer Science from Leopold-Franzens-University in Innsbruck\, Austria\
 , in 2017 and 2016\, respectively. In 2023\, he obtained his Ph.D. in Comp
 uter Science from ETH Zurich. His doctoral research focused on signal proc
 essing and machine learning in non-Euclidean domains with a focus on power
 sets\, lattices\, and posets.\n 
LOCATION:BC 420 https://plan.epfl.ch/?room==BC%20420
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR