Multi-group Agnostic PAC Learnability
Multi-group Agnostic PAC Learnability
复制标题
多组不可知 PAC 的可学习性
DOI:
--
复制
发表时间:
2021
期刊:
影响因子:
--
通讯作者:
G. Yona
中科院分区:
文献类型:
--
作者:
G. Rothblum;G. Yona
An agnostic PAC learning algorithm finds a predictor that is competitive with the best predictor in a benchmark hypothesis class, where competitiveness is measured with respect to a given loss function. However, its predictions might be quite sub-optimal for structured subgroups of individuals, such as protected demographic groups. Motivated by such fairness concerns, we study “multi-group agnostic PAC learnability”: fixing a measure of loss, a benchmark classH and a (potentially) rich collection of subgroups G, the objective is to learn a single predictor such that the loss experienced by every group g ∈ G is not much larger than the best possible loss for this group within H. Under natural conditions, we provide a characterization of the loss functions for which such a predictor is guaranteed to exist. For any such loss function we construct a learning algorithm whose sample complexity is logarithmic in the size of the collection G. Our results unify and extend previous positive and negative results from the multi-group fairness literature, which applied for specific loss functions.
登录
查看更多内容
DOI:
--
发表时间:
2018-07
期刊:
--
影响因子:
--
作者:
Úrsula Hébert-Johnson;Michael P. Kim;Omer Reingold;G. Rothblum
通讯作者:
Úrsula Hébert-Johnson;Michael P. Kim;Omer Reingold;G. Rothblum
DOI:
--
发表时间:
2022
期刊:
Innovations in Theoretical Computer Science (ITCS
影响因子:
--
作者:
Varun Gupta;Christopher Jung;Georgy Noarov;Mallesh M. Pai;Aaron Roth
通讯作者:
Aaron Roth
DOI:
--
发表时间:
2021
期刊:
Conference on Learning Theory (COLT
影响因子:
--
作者:
Jung, Christopher;Lee, Changhwa;Pai, Mallesh M;Roth, Aaron;Vohra, Rakesh
通讯作者:
Vohra, Rakesh
DOI:
10.1109/focs.2019.00016
发表时间:
2019
期刊:
60th IEEE Symposium on Foundations of Computer Science
影响因子:
--
作者:
Dwork, Cynthia;Kim, Michael P.;Reingold, Omer;Rothblum, Guy N.;Yona, Gal
通讯作者:
Yona, Gal