98 citations · 343 across the 12 of their papers we have counts for
14 papers
Exact Subspace Diffusion for Decentralized Multitask Learning
Shreya Wadehra, Roula Nassif, Stefan Vlaski
Classical paradigms for distributed learning, such as federated or decentralized gradient descent, employ consensus mechanisms to enforce homogeneity among agents. While these stra…
Quantization for decentralized learning under subspace constraints
Roula Nassif, Stefan Vlaski, Marco Carpentiero +3
In this paper, we consider decentralized optimization problems where agents have individual cost functions to minimize subject to subspace constraints that require the minimizers a…
Dencentralized learning in the presence of low-rank noise
Roula Nassif, Virginia Bordignon, Stefan Vlaski +1
Observations collected by agents in a network may be unreliable due to observation noise or interference. This paper proposes a distributed algorithm that allows each node to impro…
Diffusion LMS with Communication Delays: Stability and Performance Analysis
Fei Hua, Roula Nassif, Cédric Richard +2
We study the problem of distributed estimation over adaptive networks where communication delays exist between nodes. In particular, we investigate the diffusion Least-Mean- Square…
Multitask learning over graphs: An Approach for Distributed, Streaming Machine Learning
Roula Nassif, Stefan Vlaski, Cedric Richard +2
The problem of learning simultaneously several related tasks has received considerable attention in several domains, especially in machine learning with the so-called multitask lea…
Online Distributed Learning over Graphs with Multitask Graph-Filter Models
Fei Hua, Roula Nassif, Cédric Richard +2
In this work, we are interested in adaptive and distributed estimation of graph filters from streaming data. We formulate this problem as a consensus estimation problem over graphs…
Network Classifiers With Output Smoothing
Elsa Rizk, Roula Nassif, Ali H. Sayed
This work introduces two strategies for training network classifiers with heterogeneous agents. One strategy promotes global smoothing over the graph and a second strategy promotes…
Adaptation and learning over networks under subspace constraints -- Part II: Performance Analysis
Roula Nassif, Stefan Vlaski, Ali H. Sayed
Part I of this paper considered optimization problems over networks where agents have individual objectives to meet, or individual parameter vectors to estimate, subject to subspac…
Adaptation and learning over networks under subspace constraints -- Part I: Stability Analysis
Roula Nassif, Stefan Vlaski, Ali H. Sayed
This paper considers optimization problems over networks where agents have individual objectives to meet, or individual parameter vectors to estimate, subject to subspace constrain…
Learning over Multitask Graphs -- Part II: Performance Analysis
Roula Nassif, Stefan Vlaski, Cedric Richard +1
Part I of this paper formulated a multitask optimization problem where agents in the network have individual objectives to meet, or individual parameter vectors to estimate, subjec…
Learning over Multitask Graphs -- Part I: Stability Analysis
Roula Nassif, Stefan Vlaski, Cedric Richard +1
This paper formulates a multitask optimization problem where agents in the network have individual objectives to meet, or individual parameter vectors to estimate, subject to a smo…
Diffusion LMS for Multitask Problems with Local Linear Equality Constraints
Roula Nassif, Cédric Richard, André Ferrari +1
We consider distributed multitask learning problems over a network of agents where each agent is interested in estimating its own parameter vector, also called task, and where the…
Proximal Multitask Learning over Networks with Sparsity-inducing Coregularization
Roula Nassif, Cédric Richard, André Ferrari +1
In this work, we consider multitask learning problems where clusters of nodes are interested in estimating their own parameter vector. Cooperation among clusters is beneficial when…
Multitask diffusion adaptation over asynchronous networks
Roula Nassif, Cédric Richard, André Ferrari +1
The multitask diffusion LMS is an efficient strategy to simultaneously infer, in a collaborative manner, multiple parameter vectors. Existing works on multitask problems assume tha…