Year: 2021
Type: conference-paper
Abstract: Prediction algorithms assign numbers to individuals that are popularly understood as individual “probabilities”—what is the probability of 5-year survival after cancer diagnosis?—and which increasingly form the basis for life-altering decisions. Drawing on an understanding of computational indistinguishability developed in complexity theory and cryptography, we introduce Outcome Indistinguishability. Predictors that are Outcome Indistinguishable (OI) yield a generative model for outcomes that cannot be efficiently refuted on the basis of the real-life observations produced by .
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
Funders: National Science Foundation, Alfred P. Sloan Foundation, Simons Foundation, Microsoft Research, United States - Israel Binational Science Foundation, Adolph C. and Mary Sprague Miller Institute for Basic Research in Science, University of California Berkeley, European Commission, Council for Higher Education, Radcliffe Institute for Advanced Study, Harvard University, European Research Council, Division of Chemistry
OpenAlex ID: W3176047832