Zobrazeno 1 - 10
of 45
pro vyhledávání: '"Gaebler, Johann"'
Autor:
Gaebler, Johann D., Goel, Sharad
In observational studies of discrimination, the most common statistical approaches consider either the rate at which decisions are made (benchmark tests) or the success rate of those decisions (outcome tests). Both tests, however, have well-known sta
Externí odkaz:
http://arxiv.org/abs/2407.06539
Regulatory efforts to protect against algorithmic bias have taken on increased urgency with rapid advances in large language models (LLMs), which are machine learning models that can achieve performance rivaling human experts on a wide array of tasks
Externí odkaz:
http://arxiv.org/abs/2404.03086
Publikováno v:
Proceedings of the 39th International Conference on Machine Learning, Baltimore, Maryland, USA, PMLR 162, 2022
Recent work highlights the role of causality in designing equitable decision-making algorithms. It is not immediately clear, however, how existing causal conceptions of fairness relate to one another, or what the consequences are of using these defin
Externí odkaz:
http://arxiv.org/abs/2207.05302
Value iteration is a well-known method of solving Markov Decision Processes (MDPs) that is simple to implement and boasts strong theoretical convergence guarantees. However, the computational cost of value iteration quickly becomes infeasible as the
Externí odkaz:
http://arxiv.org/abs/2107.11053
Autor:
Tomkins, Sabina, Yao, Keniel, Gaebler, Johann, Konitzer, Tobias, Rothschild, David, Meredith, Marc, Goel, Sharad
A potential voter must incur a number of costs in order to successfully cast an in-person ballot, including the costs associated with identifying and traveling to a polling place. In order to investigate how these costs affect voting behavior, we int
Externí odkaz:
http://arxiv.org/abs/2105.01728
Publikováno v:
Statistics and Public Policy, 9 (2022) 26-48
In studies of discrimination, researchers often seek to estimate a causal effect of race or gender on outcomes. For example, in the criminal justice context, one might ask whether arrested individuals would have been subsequently charged or convicted
Externí odkaz:
http://arxiv.org/abs/2006.12460
Public and private institutions must often allocate scare resources under uncertainty. Banks, for example, extend credit to loan applicants based in part on their estimated likelihood of repaying a loan. But when the quality of information differs ac
Externí odkaz:
http://arxiv.org/abs/1911.02715
Managers, employers, policymakers, and others often seek to understand whether decisions are biased against certain groups. One popular analytic strategy is to estimate disparities after adjusting for observed covariates, typically with a regression
Externí odkaz:
http://arxiv.org/abs/1809.05651
Publikováno v:
Journal of Machine Learning Research, Vol. 24, 2023
The field of fair machine learning aims to ensure that decisions guided by algorithms are equitable. Over the last decade, several formal, mathematical definitions of fairness have gained prominence. Here we first assemble and categorize these defini
Externí odkaz:
http://arxiv.org/abs/1808.00023
Autor:
Gaebler, Johann D.1 (AUTHOR) jgaebler@fas.harvard.edu, Barghouty, Phoebe2 (AUTHOR), Vicol, Sarah3 (AUTHOR), Phillips, Cheryl2 (AUTHOR), Goel, Sharad4 (AUTHOR)
Publikováno v:
PLoS ONE. 9/13/2023, Vol. 18 Issue 9, p1-20. 20p.
