A distributed conjugate gradient online learning method over networks (Q2173726)

From MaRDI portal
scientific article
Language Label Description Also known as
English
A distributed conjugate gradient online learning method over networks
scientific article

    Statements

    A distributed conjugate gradient online learning method over networks (English)
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    17 April 2020
    0 references
    Summary: In a distributed online optimization problem with a convex constrained set over an undirected multiagent network, the local objective functions are convex and vary over time. Most of the existing methods used to solve this problem are based on the fastest gradient descent method. However, the convergence speed of these methods is decreased with an increase in the number of iterations. To accelerate the convergence speed of the algorithm, we present a distributed online conjugate gradient algorithm, different from a gradient method, in which the search directions are a set of vectors that are conjugated to each other and the step sizes are obtained through an accurate line search. We analyzed the convergence of the algorithm theoretically and obtained a regret bound of \(O\left( \sqrt{T}\right)\), where \(T\) is the number of iterations. Finally, numerical experiments conducted on a sensor network demonstrate the performance of the proposed algorithm.
    0 references
    0 references
    0 references
    0 references
    0 references

    Identifiers

    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references
    0 references