Share
Embed
Transcript
7 slides
-
Supervised Learning Without Discrimination NIPS 2016 Moritz Hardt (Google), Eric
Price (UT Austin) and Nati Srebro (TTIC) -
Data-Driven Automation • Loan approval • Healthcare premiums • Car
and home insurance premiums • Hiring • School admission • Policing strategies • Criminal sentencing • Differential service offerings • Marketing Yet for moral, legal and societal reasons, must protect from racial, gender, and other discrimination -
Non-Discrimination in Supervised Learning • Formal setup: • Available features
(e.g. credit history, payment history, rent and house purchase history, number of dependents, driving record, employment record, education, etc) • Protected attribute (e.g. race) • Prediction target (e.g. load defaulting, non-appearance, recidivism) • Learn predictor () or (, ) for • Learn based on training set , , =1.. …can mostly assume population distribution (, , ) is known • What does it mean for to be non-discriminatory? -
Blindness • Blindness: () is not a function of
(only other features) • Problem: can predict from and depend on this prediction, intentionally or inadvertently • Also: Accuracy disparity for different groups (different values of A) -
Demographic Parity = = ( | = ′)
⊥ Too strict: • What if true correlates with ? • Doesn’t allow perfect prediction = • e.g. give loans exactly to those that won’t default Not weak: • Doesn’t protect from accuracy disparity • e.g. give loans to qualified = 0 people and random = 1 people -
Suggested Notion: Equalized Odds ⊥ | Prediction does not
provide any additional information about beyond what the truth already tells us on = , = = = , = ′ • The perfect predictor, = , always satisfies equalized odds • Protects against accuracy disparity -
“Equality of Opportunity in Supervised Learning” arXiv:1610.02413 NIPS 2016 Moritz
Hardt, Eric Price and Nati Srebro • Efficiently and optimally correct discriminatory predictors to satisfy equalizes odds • Interpretation in terms of ROC curves • Incentive structure: • Shifts “cost of uncertainty” from protected group to decision maker • Incentivizes collecting features directly related to target (not via ) • Incentivizes data collection also on minority groups • Inherent limitations of oblivious tests (treating predictor as black box) • Non-identifiability of different scenarios • Why equalized odds and not calibration parity (Northpoint’s “target population errors”)