Multitask diffusion adaptation over networks with common latent representations

Abstract

Online learning with streaming data in a distributed and collaborative manner can be useful in a wide range of applications. This topic has been receiving considerable attention in recent years with emphasis on both single-task and multitask scenarios. In single-task adaptation, agents cooperate to track an objective of common interest, while in multitask adaptation agents track multiple objectives simultaneously. Regularization is one useful technique to promote and exploit similarity among tasks in the latter scenario. This work examines an alternative way to model relations among tasks by assuming that they all share a common latent feature representation. As a result, a new multitask learning formulation is presented and algorithms are developed for its solution in a distributed online manner. We present a unified framework to analyze the mean-square-error performance of the adaptive strategies, and conduct simulations to illustrate the theoretical findings and potential applications.

30 pages, 8 figures, IEEE Journal of Selected Topics in Signal Processing 2017

References in corpus (5)

• A Model of Inductive Bias Learning
• Clustered Multi-Task Learning: A Convex Formulation
• Proximal Multitask Learning over Networks with Sparsity-inducing Coregularization
• Distributed Consensus Algorithms in Sensor Networks: Link Failures and Channel Noise
• Estimation of Space-Time Varying Parameters Using a Diffusion LMS Algorithm

Cited by in corpus (6)

• Distributed Adaptive Learning of Graph Signals
• On reducing the communication cost of the diffusion LMS algorithm
• Projection-based QLP Algorithm for Efficiently Computing Low-Rank Approximation of Matrices
• Transient Theoretical Analysis of Diffusion RLS Algorithm for Cyclostationary Colored Inputs
• Affine Combination of Diffusion Strategies over Networks
• Privacy-Preserving Distributed Projection LMS for Linear Multitask Networks