no code implementations • 8 Feb 2021 • Jesse Russell
This paper explores how different ideas of racial equity in machine learning, in justice settings in particular, can present trade-offs that are difficult to solve computationally.
no code implementations • 5 Aug 2020 • Jesse Russell
Specifically, fairness in errors (both false negatives and false positives) can pose a problem of how to set weights, how to make unavoidable tradeoffs, and how to judge models that present different kinds of errors across racial groups.