Zobrazeno 1 - 10
of 47
pro vyhledávání: '"Jabbari, Shahin"'
The widespread use of machine learning models in high-stakes domains can have a major negative impact, especially on individuals who receive undesirable outcomes. Algorithmic recourse provides such individuals with suggestions of minimum-cost improve
Externí odkaz:
http://arxiv.org/abs/2410.01580
Autor:
Gray, Robert C., Villareale, Jennifer, Fox, Thomas B., Dallal, Diane H., Ontañón, Santiago, Arigo, Danielle, Jabbari, Shahin, Zhu, Jichen
Algorithmic fairness is an essential requirement as AI becomes integrated in society. In the case of social applications where AI distributes resources, algorithms often must make decisions that will benefit a subset of users, sometimes repeatedly or
Externí odkaz:
http://arxiv.org/abs/2302.09298
Autor:
Khimani, Vivek, Jabbari, Shahin
With the increased legislation around data privacy, federated learning (FL) has emerged as a promising technique that allows the clients (end-user) to collaboratively train deep learning (DL) models without transferring and storing the data in a cent
Externí odkaz:
http://arxiv.org/abs/2211.00735
As various post hoc explanation methods are increasingly being leveraged to explain complex models in high-stakes settings, it becomes critical to develop a deeper understanding of if and when the explanations output by these methods disagree with ea
Externí odkaz:
http://arxiv.org/abs/2202.01602
Autor:
Li, Zun, Jia, Feiran, Mate, Aditya, Jabbari, Shahin, Chakraborty, Mithun, Tambe, Milind, Vorobeychik, Yevgeniy
From large-scale organizations to decentralized political systems, hierarchical strategic decision making is commonplace. We introduce a novel class of structured hierarchical games (SHGs) that formally capture such hierarchical strategic interaction
Externí odkaz:
http://arxiv.org/abs/2106.04663
Autor:
Jia, Feiran, Mate, Aditya, Li, Zun, Jabbari, Shahin, Chakraborty, Mithun, Tambe, Milind, Wellman, Michael, Vorobeychik, Yevgeniy
We design and analyze a multi-level game-theoretic model of hierarchical policy interventions for epidemic control, such as those in response to the COVID-19 pandemic. Our model captures the potentially mismatched priorities among a hierarchy of poli
Externí odkaz:
http://arxiv.org/abs/2102.10646
Autor:
Agarwal, Sushant, Jabbari, Shahin, Agarwal, Chirag, Upadhyay, Sohini, Wu, Zhiwei Steven, Lakkaraju, Himabindu
As machine learning black boxes are increasingly being deployed in critical domains such as healthcare and criminal justice, there has been a growing emphasis on developing techniques for explaining these black boxes in a post hoc manner. In this wor
Externí odkaz:
http://arxiv.org/abs/2102.10618
Active screening is a common approach in controlling the spread of recurring infectious diseases such as tuberculosis and influenza. In this approach, health workers periodically select a subset of population for screening. However, given the limited
Externí odkaz:
http://arxiv.org/abs/2101.02766
Autor:
Rahmattalabi, Aida, Jabbari, Shahin, Lakkaraju, Himabindu, Vayanos, Phebe, Izenberg, Max, Brown, Ryan, Rice, Eric, Tambe, Milind
Several behavioral, social, and public health interventions, such as suicide/HIV prevention or community preparedness against natural disasters, leverage social network information to maximize outreach. Algorithmic influence maximization techniques h
Externí odkaz:
http://arxiv.org/abs/2006.07906
We study a network formation game where agents receive benefits by forming connections to other agents but also incur both direct and indirect costs from the formed connections. Specifically, once the agents have purchased their connections, an attac
Externí odkaz:
http://arxiv.org/abs/1906.00241