BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Improving Data Sub-selection for Supervised Tasks with Principal C
 ovariates Regression - Rose K. Cersonsky\, EPFL
DTSTART:20220314T143000Z
DTEND:20220314T150000Z
UID:TALK170588@talks.cam.ac.uk
CONTACT:Dr M. Simoncelli
DESCRIPTION:Data analyses based on linear methods constitute the simplest\
 , most robust\, and transparent approaches to the automatic processing of 
 large amounts of data for building supervised or unsupervised machine lear
 ning models. Principal covariates regression (PCovR) is an underappreciate
 d method that interpolates between principal component analysis and linear
  regression and can be used to conveniently reveal structure-property rela
 tions in terms of simple-to-interpret\, low-dimensional maps. We have rece
 ntly introduced methods that incorporate PCovR into two popular data selec
 tion approaches\, CUR and Farthest Point Sampling\, which iteratively iden
 tify the most diverse samples and discriminating features. While our appro
 ach is completely general\, here we focus on systems relevant to atomistic
  simulations\, chemistry\, and materials science -- fields where feature a
 nd sample selection are an increasingly common practice. Our results show 
 that these selection methods identify data subsets that out-perform their 
 unsupervised counterparts--which we demonstrate with models of increasing 
 complexity\, from ridge regression to kernel ridge regression and finally 
 feed-forward neural networks.\n\nThis work pulls from:\n\nStructure-Proper
 ty Maps with Kernel Principal Covariates Regression\;\nBA Helfrecht\, RK C
 ersonsky\, G Fraux\, M Ceriotti Machine Learning: Science and Technology 1
 \n\nImproving Sample and Feature Selection with Principal Covariates Regre
 ssion\;\nRK Cersonsky\, BA Helfrecht\, EA Engel\, S Kliavinek\, M Ceriotti
  Machine Learning: Science and Technology 2
LOCATION:Venue to be confirmed
END:VEVENT
END:VCALENDAR