A New Perspective of Accelerated Gradient Methods: The Controlled Invariant Manifold Approach

MaRDI QIDQ6437059zbMATH OpenFDO

Authors Revati Gunjal, Syed Shadab Nayyer, Alex Stankovic, Navdeep Singh

Publication date 18 May 2023

Abstract: Gradient Descent (GD) is a ubiquitous algorithm for finding the optimal solution to an optimization problem. For reduced computational complexity, the optimal solution $mathrm{x}^{\ast }$ of the optimization problem must be attained in a minimum number of iterations. For this objective, the paper proposes a genesis of an accelerated gradient algorithm through the controlled dynamical system perspective. The objective of optimally reaching the optimal solution $mathrm{x}^{\ast }$ where $mathrmablaf(x^{\ast })=0$ with a given initial condition $mathrmx(0)$ is achieved through control.

This page was built for publication: A New Perspective of Accelerated Gradient Methods: The Controlled Invariant Manifold Approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6437059)