BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Talk of Chris Russell (AWS)
DTSTART:20230221T110000
DTEND:20230221T120000
DTSTAMP:20261001T022224Z
UID:d8d00d1e26214090dcab55e867994f5391b72601a52393aba3a8384c
CATEGORIES:Conferences - Seminars
DESCRIPTION:Chris Russell (AWS)\nTitle of the talk: The limitations of al
 gorithmic fairness\n\n Abstract: This talk will take a hard look at what 
 works and doesn’t work in the field algorithmic fairness\, and the impli
 cations of existing approaches.\nWe will discuss the challenges of enforci
 ng fairness in the high-capacity models common to computer vision (Levelin
 g down in computer vision: Pareto inefficiencies in fair deep classifiers
  – CVPR’22)\nHow methods for enforcing fairness may violate anti-disc
 rimination laws (Are Two Heads the Same as One? Identifying Disparate Trea
 tment in Fair Neural Networks _ Neurips ’22)\nAs well as a general disc
 ussion about how the behavior of fair ML is often undesirable\, and  poss
 ible alternatives (https://www.wired.com/story/bias-statistics-artificial-
 intelligence-healthcare/ Wired ’23)\n\nBio: Chris Russell is an ELLIS 
 fellow and Senior Scientist at AWS. A cofounder of the Governance of Emerg
 ing Technology Research Programme at the Oxford Internet Institute\, his w
 ork on XAI is cited in the guidelines to the GDPR\, and has influenced the
  AI act. His previous work has won best paper award at ICRA\; ECCV\; and B
 MVC.\n 
LOCATION:ELA 2 https://plan.epfl.ch/?room==ELA%202
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR