Zobrazeno 1 - 10
of 1 150
pro vyhledávání: '"Asoodeh A"'
Autor:
Ghoukasian, Hrad, Asoodeh, Shahab
In this work, we investigate binary classification under the constraints of both differential privacy and fairness. We first propose an algorithm based on the decoupling technique for learning a classifier with only fairness guarantee. This algorithm
Externí odkaz:
http://arxiv.org/abs/2402.15603
We study the problem of hypothesis selection under the constraint of local differential privacy. Given a class $\mathcal{F}$ of $k$ distributions and a set of i.i.d. samples from an unknown distribution $h$, the goal of hypothesis selection is to pic
Externí odkaz:
http://arxiv.org/abs/2312.05645
Autor:
Asoodeh, Shahab, Diaz, Mario
The Noisy-SGD algorithm is widely used for privately training machine learning models. Traditional privacy analyses of this algorithm assume that the internal state is publicly revealed, resulting in privacy loss bounds that increase indefinitely wit
Externí odkaz:
http://arxiv.org/abs/2305.09903
Publikováno v:
2023 IEEE International Symposium on Information Theory (ISIT), Taipei, Taiwan, 2023, pp. 1478-1483
The information bottleneck (IB) method aims to find compressed representations of a variable $X$ that retain the most relevant information about a target variable $Y$. We show that for a wide family of distributions -- namely, when $Y$ is generated b
Externí odkaz:
http://arxiv.org/abs/2305.07000
Publikováno v:
Open Geosciences, Vol 5, Iss 4, Pp 508-513 (2013)
Externí odkaz:
https://doaj.org/article/a5e8148cec17489c8371d675f62b4059
Autor:
Asoodeh, Shahab, Zhang, Huanyu
We investigate the contraction properties of locally differentially private mechanisms. More specifically, we derive tight upper bounds on the divergence between $PK$ and $QK$ output distributions of an $\epsilon$-LDP mechanism $K$ in terms of a dive
Externí odkaz:
http://arxiv.org/abs/2210.13386
Autor:
Alghamdi, Wael, Asoodeh, Shahab, Calmon, Flavio P., Gomez, Juan Felipe, Kosut, Oliver, Sankar, Lalitha, Wei, Fei
We introduce a new differential privacy (DP) accountant called the saddle-point accountant (SPA). SPA approximates privacy guarantees for the composition of DP mechanisms in an accurate and fast manner. Our approach is inspired by the saddle-point me
Externí odkaz:
http://arxiv.org/abs/2208.09595
Most differential privacy mechanisms are applied (i.e., composed) numerous times on sensitive data. We study the design of optimal differential privacy mechanisms in the limit of a large number of compositions. As a consequence of the law of large nu
Externí odkaz:
http://arxiv.org/abs/2207.00420
Autor:
Alghamdi, Wael, Hsu, Hsiang, Jeong, Haewon, Wang, Hao, Michalak, P. Winston, Asoodeh, Shahab, Calmon, Flavio P.
We consider the problem of producing fair probabilistic classifiers for multi-class classification tasks. We formulate this problem in terms of "projecting" a pre-trained (and potentially unfair) classifier onto the set of models that satisfy target
Externí odkaz:
http://arxiv.org/abs/2206.07801
Autor:
Fatemeh Shahab-Navaei, Ahmad Asoodeh
Publikováno v:
Scientific Reports, Vol 13, Iss 1, Pp 1-14 (2023)
Abstract This study aimed to produce stable propolis nanoparticles with a size below 100 nm, suitable for various applications in industries such as pharmaceuticals, medicine, cosmetics, food, and packaging. To achieve this, propolis solid lipid nano
Externí odkaz:
https://doaj.org/article/dfafe947dbff44b18e037ee6fa074265