Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Girgis, Antonious M."'
Autor:
Hard, Andrew, Girgis, Antonious M., Amid, Ehsan, Augenstein, Sean, McConnaughey, Lara, Mathews, Rajiv, Anil, Rohan
How well do existing federated learning algorithms learn from client devices that return model updates with a significant time delay? Is it even possible to learn effectively from clients that report back minutes, hours, or days after being scheduled
Externí odkaz:
http://arxiv.org/abs/2403.09086
Autor:
Girgis, Antonious M., Diggavi, Suhas
We study differentially private distributed optimization under communication constraints. A server using SGD for optimization aggregates the client-side local gradients for model updates using distributed mean estimation (DME). We develop a communica
Externí odkaz:
http://arxiv.org/abs/2302.11152
In this paper, we propose differentially private algorithms for the problem of stochastic linear bandits in the central, local and shuffled models. In the central model, we achieve almost the same regret as the optimal non-private algorithms, which m
Externí odkaz:
http://arxiv.org/abs/2207.03445
A distinguishing characteristic of federated learning is that the (local) client data could have statistical heterogeneity. This heterogeneity has motivated the design of personalized learning, where individual (personalized) models are trained, thro
Externí odkaz:
http://arxiv.org/abs/2207.01771
We study privacy in a distributed learning framework, where clients collaboratively build a learning model iteratively through interactions with a server from whom we need privacy. Motivated by stochastic optimization and the federated learning (FL)
Externí odkaz:
http://arxiv.org/abs/2107.08763
Autor:
Wang, Jianyu, Charles, Zachary, Xu, Zheng, Joshi, Gauri, McMahan, H. Brendan, Arcas, Blaise Aguera y, Al-Shedivat, Maruan, Andrew, Galen, Avestimehr, Salman, Daly, Katharine, Data, Deepesh, Diggavi, Suhas, Eichner, Hubert, Gadhikar, Advait, Garrett, Zachary, Girgis, Antonious M., Hanzely, Filip, Hard, Andrew, He, Chaoyang, Horvath, Samuel, Huo, Zhouyuan, Ingerman, Alex, Jaggi, Martin, Javidi, Tara, Kairouz, Peter, Kale, Satyen, Karimireddy, Sai Praneeth, Konecny, Jakub, Koyejo, Sanmi, Li, Tian, Liu, Luyang, Mohri, Mehryar, Qi, Hang, Reddi, Sashank J., Richtarik, Peter, Singhal, Karan, Smith, Virginia, Soltanolkotabi, Mahdi, Song, Weikang, Suresh, Ananda Theertha, Stich, Sebastian U., Talwalkar, Ameet, Wang, Hongyi, Woodworth, Blake, Wu, Shanshan, Yu, Felix X., Yuan, Honglin, Zaheer, Manzil, Zhang, Mi, Zhang, Tong, Zheng, Chunxiang, Zhu, Chen, Zhu, Wennan
Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data, motivated by and designed for privacy protection. The distributed learning process can be formulated as solving f
Externí odkaz:
http://arxiv.org/abs/2107.06917
The central question studied in this paper is Renyi Differential Privacy (RDP) guarantees for general discrete local mechanisms in the shuffle privacy model. In the shuffle model, each of the $n$ clients randomizes its response using a local differen
Externí odkaz:
http://arxiv.org/abs/2105.05180
We consider a distributed empirical risk minimization (ERM) optimization problem with communication efficiency and privacy requirements, motivated by the federated learning (FL) framework. Unique challenges to the traditional ERM problem in the conte
Externí odkaz:
http://arxiv.org/abs/2008.07180
Autor:
Girgis, Antonious M., Data, Deepesh, Chaudhuri, Kamalika, Fragouli, Christina, Diggavi, Suhas
This work examines a novel question: how much randomness is needed to achieve local differential privacy (LDP)? A motivating scenario is providing {\em multiple levels of privacy} to multiple analysts, either for distribution or for heavy-hitter esti
Externí odkaz:
http://arxiv.org/abs/2005.11651
In this paper, an interference network with arbitrary number of transmitters and receivers is studied, where each transmitter is equipped with a finite size cache. We obtain an information-theoretic lower bound on both the peak normalized delivery ti
Externí odkaz:
http://arxiv.org/abs/1812.02388