Lensing Machines: Representing Perspective in Latent Variable Models

no code implementations • 20 Jan 2022 • Karthik Dinakar, Henry Lieberman

Many datasets represent a combination of different ways of looking at the same data that lead to different generalizations.

Interventions over Predictions: Reframing the Ethical Debate for Actuarial Risk Assessment

no code implementations • 21 Dec 2017 • Chelsea Barabas, Karthik Dinakar, Joichi Ito, Madars Virza, Jonathan Zittrain

Actuarial risk assessments might be unduly perceived as a neutral way to counteract implicit bias and increase the fairness of decisions made at almost every juncture of the criminal justice system, from pretrial release to sentencing, parole and probation.

BIG-bench Machine Learning Causal Inference +1