Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Gitiaux, Xavier"'
Data owners face increasing liability for how the use of their data could harm under-priviliged communities. Stakeholders would like to identify the characteristics of data that lead to algorithms being biased against any particular demographic group
Externí odkaz:
http://arxiv.org/abs/2208.07918
Autor:
Gitiaux, Xavier, Rangwala, Huzefa
To avoid discriminatory uses of their data, organizations can learn to map them into a representation that filters out information related to sensitive attributes. However, all existing methods in fair representation learning generate a fairness-info
Externí odkaz:
http://arxiv.org/abs/2204.12556
We consider social resource allocations that deliver an array of scarce supports to a diverse population. Such allocations pervade social service delivery, such as provision of homeless services, assignment of refugees to cities, among others. At iss
Externí odkaz:
http://arxiv.org/abs/2202.12334
We develop a recursive algorithm to generalize the quantum SWAP test for an arbitrary number $m$ of quantum states requiring $O(m)$ controlled-swap (CSWAP) gates and $O(\log m)$ ancillary qubits. We construct a quantum circuit able to simultaneously
Externí odkaz:
http://arxiv.org/abs/2110.13261
Autor:
Gitiaux, Xavier, Khant, Aditya, Beyrami, Ebrahim, Reddy, Chandan, Gupchup, Jayant, Cutler, Ross
Noise suppression models running in production environments are commonly trained on publicly available datasets. However, this approach leads to regressions due to the lack of training/testing on representative customer data. Moreover, due to privacy
Externí odkaz:
http://arxiv.org/abs/2110.04391
Autor:
Gitiaux, Xavier, Rangwala, Huzefa
Organizations that collect and sell data face increasing scrutiny for the discriminatory use of data. We propose a novel unsupervised approach to transform data into a compressed binary representation independent of sensitive attributes. We show that
Externí odkaz:
http://arxiv.org/abs/2105.14044
Autor:
Gitiaux, Xavier, Rangwala, Huzefa
Organizations that own data face increasing legal liability for its discriminatory use against protected demographic groups, extending to contractual transactions involving third parties access and use of the data. This is problematic, since the orig
Externí odkaz:
http://arxiv.org/abs/2006.08788
Autor:
Jungbluth, Anna, Gitiaux, Xavier, Maloney, Shane A., Shneider, Carl, Wright, Paul J., Kalaitzis, Alfredo, Deudon, Michel, Baydin, Atılım Güneş, Gal, Yarin, Muñoz-Jaramillo, Andrés
Breakthroughs in our understanding of physical phenomena have traditionally followed improvements in instrumentation. Studies of the magnetic field of the Sun, and its influence on the solar dynamo and space weather events, have benefited from improv
Externí odkaz:
http://arxiv.org/abs/1911.01490
Autor:
Gitiaux, Xavier, Maloney, Shane A., Jungbluth, Anna, Shneider, Carl, Wright, Paul J., Baydin, Atılım Güneş, Deudon, Michel, Gal, Yarin, Kalaitzis, Alfredo, Muñoz-Jaramillo, Andrés
Machine learning techniques have been successfully applied to super-resolution tasks on natural images where visually pleasing results are sufficient. However in many scientific domains this is not adequate and estimations of errors and uncertainties
Externí odkaz:
http://arxiv.org/abs/1911.01486
Autor:
Gitiaux, Xavier, Rangwala, Huzefa
Machine learning algorithms are increasingly involved in sensitive decision-making process with adversarial implications on individuals. This paper presents mdfa, an approach that identifies the characteristics of the victims of a classifier's discri
Externí odkaz:
http://arxiv.org/abs/1903.07609