Fairness and Machine Learning: Limitations and OpportunitiesMIT Press, 19 dec 2023 - 340 pagina's An introduction to the intellectual foundations and practical utility of the recent work on fairness and machine learning. Fairness and Machine Learning introduces advanced undergraduate and graduate students to the intellectual foundations of this recently emergent field, drawing on a diverse range of disciplinary perspectives to identify the opportunities and hazards of automated decision-making. It surveys the risks in many applications of machine learning and provides a review of an emerging set of proposed solutions, showing how even well-intentioned applications may give rise to objectionable results. It covers the statistical and causal measures used to evaluate the fairness of machine learning models as well as the procedural and substantive aspects of decision-making that are core to debates about fairness, including a review of legal and philosophical perspectives on discrimination. This incisive textbook prepares students of machine learning to do quantitative work on fairness while reflecting critically on its foundations and its practical utility. • Introduces the technical and normative foundations of fairness in automated decision-making • Covers the formal and computational methods for characterizing and addressing problems • Provides a critical assessment of their intellectual foundations and practical utility • Features rich pedagogy and extensive instructor resources |
Inhoudsopgave
When Is Automated Decision Making Legitimate? | 25 |
Classification | 49 |
4 | 50 |
Relative Notions of Fairness | 83 |
Tensions between the Different Views | 93 |
Connecting Statistical and Moral Notions of Fairness | 100 |
Alternatives for Realizing the Middle View of Equality of Opportunity | 109 |
Causal Models | 117 |
Concluding Thoughts | 182 |
Studies of DecisionMaking Processes and Organizations | 200 |
Three Types of Harms | 206 |
Mechanisms of Discrimination | 212 |
Looking Ahead | 219 |
Three Levels of Discrimination | 225 |
Structural Interventions for Fair Machine Learning | 234 |
Concluding Thoughts | 245 |
Interventions and Causal Effects | 123 |
Counterfactuals | 132 |
6 | 138 |
Understanding United States Antidiscrimination Law | 151 |
A Few Basics of the American Legal System | 157 |
How the Law Conceives of Discrimination | 163 |
Regulating Machine Learning | 172 |
Overige edities - Alles bekijken
Fairness and Machine Learning: Limitations and Opportunities Solon Barocas,Moritz Hardt,Arvind Narayanan Gedeeltelijke weergave - 2023 |
Veelvoorkomende woorden en zinsdelen
accuracy achieve admissions algorithmic antidiscrimination applicants arXiv assessment automated benchmark datasets bias biases binary body mass index causal graph chapter characteristics civil rights classifier computer vision conditional conditional independence conditional probability confounding counterfactual courts credit score criteria criterion decision makers decision subjects department choice disability discrimination discriminatory discussed disparate impact disparate treatment distribution effect employer employment equality of opportunity equality of outcome example Facebook fairness false positive rate formal gender goals harms hiring human ImageNet independence individuals inequality interventions machine learning measure middle view node normative notion observed optimal performance plaintiff population potential outcomes predictive probability problem proxies question race racial random variables reason relevant requires result risk score ROC curve sample sensitive attribute similar Simpson's paradox social specific statistical structural causal model supervised learning target variable threshold tion Title IX users view of equality
