Learning Non-Discriminatory Predictors
نویسندگان
چکیده
We consider learning a predictor which is non-discriminatory with respect to a “protected attribute” according to the notion of “equalized odds” proposed by Hardt et al. [2016]. We study the problem of learning such a non-discriminatory predictor from a finite training set, both statistically and computationally. We show that a post-hoc correction approach, as suggested by Hardt et al, can be highly suboptimal, present a nearly-optimal statistical procedure, argue that the associated computational problem is intractable, and suggest a second moment relaxation of the non-discrimination definition for which learning is tractable.
منابع مشابه
Research Paper: A Comparison of Citation Metrics to Machine Learning Filters for the Identification of High Quality MEDLINE Documents
OBJECTIVE The present study explores the discriminatory performance of existing and novel gold-standard-specific machine learning (GSS-ML) focused filter models (i.e., models built specifically for a retrieval task and a gold standard against which they are evaluated) and compares their performance to citation count and impact factors, and non-specific machine learning (NS-ML) models (i.e., mod...
متن کاملNon-Discriminatory Machine Learning through Convex Fairness Criteria
Biased decision making by machine learning systems is increasingly recognized as an important issue. Recently, techniques have been proposed to learn non-discriminatory classifiers by enforcing constraints in the training phase. Such constraints are either non-convex in nature (posing computational difficulties) or don’t have a clear probabilistic interpretation. Moreover, the techniques offer ...
متن کاملFairness in Supervised Learning: An Information Theoretic Approach
Automated decision making systems are increasingly being used in real-world applications. In these systems for the most part, the decision rules are derived by minimizing the training error on the available historical data. Therefore, if there is a bias related to a sensitive attribute such as gender, race, religion, etc. in the data, say, due to cultural/historical discriminatory practices aga...
متن کاملKindergarten risk factors, cognitive factors, and teacher judgments as predictors of early reading in Dutch.
This study focused on the predictive value of risk factors, cognitive factors, and teachers' judgments in a sample of 462 kindergartners for their early reading skills and reading failure at the beginning of Grade 1. With respect to risk factors, enrollment in speech-language therapy, history of dyslexia or speech-language problems in the family, and the role of gender were considered. None of ...
متن کاملA Comparison of Citation Metrics to Machine Learning Filters for the Identification of High Quality MEDLINE Documents
Design: Three gold standard corpora were constructed using the SSOAB bibliography, the ACPJ-cited treatment articles, and the ACPJ-cited etiology articles. Citation counts and impact factors were obtained for each article. Support vector machine models were used to classify the articles using combinations of content, impact factors, and citation counts as predictors. Measurements: Discriminator...
متن کامل