A Closed Loop Gradient Descent Algorithm applied to Rosenbrock's function

Subhransu S. Bhattacharjee, Ian R. Petersen

    Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

    4 Citations (Scopus)

    Abstract

    We introduce a novel adaptive damping technique for an inertial gradient system which finds application as a gradient descent algorithm for unconstrained optimisation. In an example using the non-convex Rosenbrock's function, we show an improvement on existing momentum-based gradient optimisation methods. Also using Lyapunov stability analysis, we demonstrate the performance of the continuous-time version of the algorithm. Using numerical simulations, we consider the performance of its discrete-time counterpart obtained by using the symplectic Euler method of discretisation.

    Original languageEnglish
    Title of host publication2021 Australian and New Zealand Control Conference, ANZCC 2021
    PublisherInstitute of Electrical and Electronics Engineers Inc.
    Pages137-142
    Number of pages6
    ISBN (Electronic)9781665416504
    DOIs
    Publication statusPublished - 2021
    Event2021 Australian and New Zealand Control Conference, ANZCC 2021 - Gold Coast, Australia
    Duration: 25 Nov 202126 Nov 2021

    Publication series

    Name2021 Australian and New Zealand Control Conference, ANZCC 2021

    Conference

    Conference2021 Australian and New Zealand Control Conference, ANZCC 2021
    Country/TerritoryAustralia
    CityGold Coast
    Period25/11/2126/11/21

    Fingerprint

    Dive into the research topics of 'A Closed Loop Gradient Descent Algorithm applied to Rosenbrock's function'. Together they form a unique fingerprint.

    Cite this