TY - GEN
T1 - Meritocratic fairness for cross-population selection
AU - Kearns, Michael
AU - Roth, Aaron
AU - Wu, Zhiwei Steven
N1 - Publisher Copyright:
© Copyright 2017 by the author(s).
Copyright:
Copyright 2018 Elsevier B.V., All rights reserved.
PY - 2017
Y1 - 2017
N2 - We consider the problem of selecting a pool of individuals from several populations with incomparable skills (e.g. soccer players, mathematicians, and singers) in a fair manner. The quality of an individual is defined to be their relative rank (by cumulative distribution value) within their own population, which permits cross-population comparisons. We study algorithms which attempt to select the highest quality subset despite the fact that true CDF values are not known, and can only be estimated from the finite pool of candidates. Specifically, we quantify the regret in quality imposed by "meritocratic" notions of fairness, which require that individuals are selected with probability that is monotonically increasing in their true quality. We give algorithms with provable fairness and regret guarantees, as well as lower bounds, and provide empirical results which suggest that our algorithms perform better than the theory suggests.
AB - We consider the problem of selecting a pool of individuals from several populations with incomparable skills (e.g. soccer players, mathematicians, and singers) in a fair manner. The quality of an individual is defined to be their relative rank (by cumulative distribution value) within their own population, which permits cross-population comparisons. We study algorithms which attempt to select the highest quality subset despite the fact that true CDF values are not known, and can only be estimated from the finite pool of candidates. Specifically, we quantify the regret in quality imposed by "meritocratic" notions of fairness, which require that individuals are selected with probability that is monotonically increasing in their true quality. We give algorithms with provable fairness and regret guarantees, as well as lower bounds, and provide empirical results which suggest that our algorithms perform better than the theory suggests.
UR - http://www.scopus.com/inward/record.url?scp=85048404708&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048404708&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85048404708
T3 - 34th International Conference on Machine Learning, ICML 2017
SP - 2905
EP - 2913
BT - 34th International Conference on Machine Learning, ICML 2017
PB - International Machine Learning Society (IMLS)
T2 - 34th International Conference on Machine Learning, ICML 2017
Y2 - 6 August 2017 through 11 August 2017
ER -