Swarm-based gradient descent method for non-convex optimization

DOI10.1090/CAMS/42MaRDI QIDQ6660969zbMATH OpenFDO

Authors Eitan Tadmor, Anil Zenginoglu

Publication date 10 January 2025

Published in Communications of the American Mathematical Society (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1090/CAMS/42

zbMATH Keywords

backtrackingconvergence analysisgradient descentoptimizationswarming

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) Nonconvex programming, global optimization (90C26) Population dynamics (general) (92D25)

Recommendations

• Swarm-based optimization with random descent
• Swarm-based gradient descent meets simulated annealing
• Swarm gradient dynamics for global optimization: the mean-field limit case
• Swarming for faster convergence in stochastic optimization
• On the global convergence of particle swarm optimization methods

Cites work

• A consensus-based global optimization method for high dimensional machine learning problems
• A consensus-based model for global optimization and its mean-field limit
• A literature survey of benchmark functions for global optimisation problems
• An adaptive gradient method with energy and momentum
• An analytical framework for consensus-based global optimization method
• Characterizations of Łojasiewicz inequalities: Subgradient flows, talweg, convexity
• Convergence and error estimates for time-discrete consensus-based optimization algorithms
• Convergence Conditions for Ascent Methods
• Convergence of a first-order consensus-based global optimization algorithm
• scientific article; zbMATH DE number 48722 (Why is no real title available?)
• scientific article; zbMATH DE number 1158743 (Why is no real title available?)
• Minimization of functions having Lipschitz continuous first partial derivatives
• On semi- and subanalytic geometry
• On the mathematics of swarming: emergent behavior in alignment dynamics
• Swarm-based optimization with random descent
• The Large-Time Behavior of the Scalar, Genuinely Nonlinear Lax-Friedrichs Scheme
• Trends in Consensus-Based Optimization

Cited in

(7)

• Swarm gradient dynamics for global optimization: the mean-field limit case
• Swarm-based optimization with random descent
• Swarm-based gradient descent meets simulated annealing
• Energy-stable swarm-based inertial algorithms for optimization
• Optimization-based transionospheric SAR autofocus with screen projection precursor
• Stability of Finite-Batch Particle Mean-Field Variational Inference Beyond Strong Convexity
• Expansive natural neural gradient flows for energy minimization

This page was built for publication: Swarm-based gradient descent method for non-convex optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6660969)