BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Counterfactual fairness (CANCELLED) - Joshua Loftus (London School
  of Economics)
DTSTART:20230203T140000Z
DTEND:20230203T150000Z
UID:TALK194896@talks.cam.ac.uk
CONTACT:Qingyuan Zhao
DESCRIPTION:Structural causal models are powerful tools for understanding 
 algorithmic fairness. Strong causal assumptions can be more interpretable 
 and enable transparent deliberation over algorithm design choices. This ta
 lk illustrates an approach through examples including defining fairness fo
 r predictive algorithms\, fair policy optimization\, and intersectional fa
 irness. While these examples focus on fairness\, causal modeling can be ap
 plied in similar ways toward achieving other values or objectives in respo
 nsible machine learning or data-driven decisions broadly.
LOCATION:MR12\, Centre for Mathematical Sciences
END:VEVENT
END:VCALENDAR