R
Roula Nassif
Researcher at École Polytechnique Fédérale de Lausanne
Publications - 39
Citations - 672
Roula Nassif is an academic researcher from École Polytechnique Fédérale de Lausanne. The author has contributed to research in topics: Optimization problem & Distributed algorithm. The author has an hindex of 12, co-authored 35 publications receiving 486 citations. Previous affiliations of Roula Nassif include Centre national de la recherche scientifique & American University of Beirut.
Papers
More filters
Journal ArticleDOI
Proximal Multitask Learning Over Networks With Sparsity-Inducing Coregularization
TL;DR: This work considers multitask learning problems where clusters of nodes are interested in estimating their own parameter vector and proposes a fully distributed algorithm that relies on minimizing a global mean-square error criterion regularized by nondifferentiable terms to promote cooperation among neighboring clusters.
Journal ArticleDOI
Multitask Learning Over Graphs: An Approach for Distributed, Streaming Machine Learning
TL;DR: MTL is an approach to inductive transfer learning (using what is learned for one problem to assist with another problem), and it helps improve generalization performance relative to learning each task separately by using the domain information contained in the training signals of related tasks as an inductive bias.
Journal ArticleDOI
Diffusion LMS for Multitask Problems With Local Linear Equality Constraints
TL;DR: In this article, an adaptive stochastic algorithm based on the projection gradient method and diffusion strategies is proposed to optimize the individual costs subject to all constraints, including linear equality constraints.
Journal ArticleDOI
Multitask Diffusion Adaptation Over Asynchronous Networks
TL;DR: In this article, a model for the solution of multitask problems over asynchronous networks is described and a detailed mean and mean-square error analysis is carried out, which shows that sufficiently small step-sizes can still ensure both stability and performance.
Posted Content
Multitask diffusion adaptation over asynchronous networks
TL;DR: A model for the solution of multitask problems over asynchronous networks is described and a detailed mean and mean-square error analysis is carried out to show that sufficiently small step-sizes can still ensure both stability and performance.