scientific article; zbMATH DE number 7523120

MaRDI QIDQ5074079zbMATH OpenFDO

Authors Tuyen Trung Truong, Hang-Tuan Nguyen

Publication date 6 May 2022

Full work available at URL https://www.heldermann.de/MTA/MTA07/MTA071/mta07003.htm

zbMATH Keywords

backtrackingdeep learningglobal convergencegradient descentline search methodoptimisationrandom dynamical systems

Mathematics Subject Classification ID

Numerical methods in optimal control (49Mxx) Numerical methods for mathematical programming, optimization and variational techniques (65Kxx) Artificial intelligence (68Txx) Computing methodologies and applications (68Uxx)

Cites work

• A Stochastic Approximation Method
• An inertial Newton algorithm for deep learning
• Analysis of the gradient method with an Armijo-Wolfe line search on a class of non-smooth convex functions
• Backtracking gradient descent method and some applications in large scale optimisation. II: Algorithms and experiments
• Cauchy's method of minimization
• Convergence Conditions for Ascent Methods
• Convergence of descent methods for semi-algebraic and tame problems: proximal algorithms, forward-backward splitting, and regularized Gauss-Seidel methods
• Convergence of the Iterates of Descent Methods for Analytic Cost Functions
• Gradient descent only converges to minimizers: non-isolated critical points and invariant regions
• Gradient methods of maximization
• scientific article; zbMATH DE number 1818892 (Why is no real title available?)
• scientific article; zbMATH DE number 5060482 (Why is no real title available?)
• Introductory lectures on convex optimization. A basic course.
• Limit Points of Sequences in Metric Spaces
• Minimization of functions having Lipschitz continuous first partial derivatives
• Optimization
• Optimization and dynamical systems
• Optimization methods for large-scale machine learning
• The Boosted Difference of Convex Functions Algorithm for Nonsmooth Functions
• THE HEAVY BALL WITH FRICTION METHOD, I. THE CONTINUOUS DYNAMICAL SYSTEM: GLOBAL EXPLORATION OF THE LOCAL MINIMA OF A REAL-VALUED FUNCTION BY ASYMPTOTIC ANALYSIS OF A DISSIPATIVE DYNAMICAL SYSTEM
• The method of steepest descent for non-linear minimization problems

Cited in

(2)

• A fast and simple modification of Newton's method avoiding saddle points
• An oracle gradient regularized Newton method for quadratic measurements regression

Describes a project that uses

Uses Software

• CIFAR
• MBT-optimizer
• GitHub

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5074079)