Zobrazeno 1 - 10
of 685
pro vyhledávání: '"A, Stoyanovich"'
Data missingness is a practical challenge of sustained interest to the scientific community. In this paper, we present Shades-of-Null, an evaluation suite for responsible missing value imputation. Our work is novel in two ways (i) we model realistic
Externí odkaz:
http://arxiv.org/abs/2409.07510
Responsible AI (RAI) is the science and the practice of making the design, development, and use of AI socially sustainable: of reaping the benefits of innovation while controlling the risks. Naturally, industry practitioners play a decisive role in o
Externí odkaz:
http://arxiv.org/abs/2407.14686
Database queries are often used to select and rank items as decision support for many applications. As automated decision-making tools become more prevalent, there is a growing recognition of the need to diversify their outcomes. In this paper, we de
Externí odkaz:
http://arxiv.org/abs/2403.17786
Algorithmic recourse -- providing recommendations to those affected negatively by the outcome of an algorithmic system on how they can take action and change that outcome -- has gained attention as a means of giving persons agency in their interactio
Externí odkaz:
http://arxiv.org/abs/2401.16088
Algorithmic decisions in critical domains such as hiring, college admissions, and lending are often based on rankings. Because of the impact these decisions have on individuals, organizations, and population groups, there is a need to understand them
Externí odkaz:
http://arxiv.org/abs/2401.16744
Counterfactuals and counterfactual reasoning underpin numerous techniques for auditing and understanding artificial intelligence (AI) systems. The traditional paradigm for counterfactual reasoning in this literature is the interventional counterfactu
Externí odkaz:
http://arxiv.org/abs/2401.13935
Differentially private (DP) mechanisms have been deployed in a variety of high-impact social settings (perhaps most notably by the U.S. Census). Since all DP mechanisms involve adding noise to results of statistical queries, they are expected to impa
Externí odkaz:
http://arxiv.org/abs/2312.11712
Algorithmic systems are often called upon to assist in high-stakes decision making. In light of this, algorithmic recourse, the principle wherein individuals should be able to take action against an undesirable outcome made by an algorithmic system,
Externí odkaz:
http://arxiv.org/abs/2309.06969
Autor:
Khan, Falaah Arif, Stoyanovich, Julia
In this paper we revisit the bias-variance decomposition of model error from the perspective of designing a fair classifier: we are motivated by the widely held socio-technical belief that noise variance in large datasets in social domains tracks dem
Externí odkaz:
http://arxiv.org/abs/2302.08704
Autor:
Bell, Andrew, Bynum, Lucius, Drushchak, Nazarii, Herasymova, Tetiana, Rosenblatt, Lucas, Stoyanovich, Julia
The ``impossibility theorem'' -- which is considered foundational in algorithmic fairness literature -- asserts that there must be trade-offs between common notions of fairness and performance when fitting statistical models, except in two special ca
Externí odkaz:
http://arxiv.org/abs/2302.06347