no code implementations • 29 Sep 2023 • Martin Pelikan, Sheikh Shams Azam, Vitaly Feldman, Jan "Honza" Silovsky, Kunal Talwar, Tatiana Likhomanenko
($4. 5$, $10^{-9}$)-$\textbf{DP}$) with a 1. 3% (resp.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
no code implementations • 22 Sep 2023 • Sheikh Shams Azam, Tatiana Likhomanenko, Martin Pelikan, Jan "Honza" Silovsky
In this paper, we start by training End-to-End Automatic Speech Recognition (ASR) models using Federated Learning (FL) and examining the fundamental considerations that can be pivotal in minimizing the performance gap in terms of word error rate between models trained using FL versus their centralized counterpart.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • ICLR 2022 • Sheikh Shams Azam, Seyyedali Hosseinalipour, Qiang Qiu, Christopher Brinton
In this paper, we question the rationale behind propagating large numbers of parameters through a distributed system during federated learning.
1 code implementation • 7 Sep 2021 • Frank Po-Chen Lin, Seyyedali Hosseinalipour, Sheikh Shams Azam, Christopher G. Brinton, Nicolò Michelusi
Federated learning has emerged as a popular technique for distributing model training across the network edge.
1 code implementation • 18 Mar 2021 • Frank Po-Chen Lin, Seyyedali Hosseinalipour, Sheikh Shams Azam, Christopher G. Brinton, Nicolo Michelusi
Federated learning has emerged as a popular technique for distributing machine learning (ML) model training across the wireless edge.
1 code implementation • 5 Oct 2020 • Sheikh Shams Azam, Taejin Kim, Seyyedali Hosseinalipour, Carlee Joe-Wong, Saurabh Bagchi, Christopher Brinton
We study the problem of learning representations that are private yet informative, i. e., provide information about intended "ally" targets while hiding sensitive "adversary" attributes.
1 code implementation • 18 Jul 2020 • Seyyedali Hosseinalipour, Sheikh Shams Azam, Christopher G. Brinton, Nicolo Michelusi, Vaneet Aggarwal, David J. Love, Huaiyu Dai
We derive the upper bound of convergence for MH-FL with respect to parameters of the network topology (e. g., the spectral radius) and the learning algorithm (e. g., the number of D2D rounds in different clusters).
no code implementations • 30 Apr 2018 • Sheikh Shams Azam, Manoj Raju, Venkatesh Pagidimarri, Vamsi Kasivajjala
Over the past decade, there has been a steep rise in the data-driven analysis in major areas of medicine, such as clinical decision support system, survival analysis, patient similarity analysis, image analytics etc.