Optimization by linear kinetic equations and mean-field Langevin dynamics

DOI10.1142/S0218202524500428MaRDI QIDQ6669902

Publication date: 22 January 2025

Published in: M$^3$AS. Mathematical Models \& Methods in Applied Sciences (Search for Journal in Brave)

zbMATH Keywords

sampling global optimization simulated annealing entropy inequalities stochastic gradient descent linear Boltzmann equation mean-field Langevin dynamics

Mathematics Subject Classification ID

Sampling theory, sample surveys (62D05) Numerical optimization and variational techniques (65K10) Kinetic theory of gases in time-dependent statistical mechanics (82C40) Boltzmann equations (35Q20)

Cites Work

Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Title not available (Why is that?)
Optimization by Simulated Annealing
Modified logarithmic Sobolev inequalities in discrete settings
Spectral gap and coercivity estimates for linearized Boltzmann collision operators without angular cutoff
Simulated annealing via Sobolev inequalities
The Boltzmann equation with a soft potential. I: Linear, spatially- homogeneous
Laplace's method revisited: Weak convergence of probability measures
Weak convergence and optimal scaling of random walk Metropolis algorithms
Optimal scaling for various Metropolis-Hastings algorithms.
Hypocoercivity in metastable settings and kinetic simulated annealing
Structure preserving schemes for nonlinear Fokker-Planck equations and applications
On the rate of convergence to equilibrium for the linear Boltzmann equation with soft potentials
Optimal scaling and diffusion limits for the Langevin algorithm in high dimensions
Simulated annealing algorithms for continuous global optimization: Convergence conditions
Convergence and error estimates for time-discrete consensus-based optimization algorithms
Mean-field Langevin dynamics and energy landscape of neural networks
Binary interaction methods for high dimensional global optimization and machine learning
Entropy dissipation estimates for the linear Boltzmann operator
General relative entropy inequality: an illustration on growth models
ENTROPIC METHODS FOR THE STUDY OF THE LONG TIME BEHAVIOR OF KINETIC EQUATIONS
A consensus-based model for global optimization and its mean-field limit
Consensus-based optimization on hypersurfaces: Well-posedness and mean-field limit
Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of Images
Diffusions for Global Optimization
Cooling Schedules for Optimal Annealing
On asymptotics of the Boltzmann equation when the collisions become grazing
Convergence theorems for a class of simulated annealing algorithms on ℝ^d
An analytical framework for consensus-based global optimization method
A consensus-based global optimization method for high dimensional machine learning problems
Trends in Consensus-Based Optimization
Anisotropic Diffusion in Consensus-Based Optimization on the Sphere
Non-Maxwellian kinetic equations modeling the dynamics of wealth distribution
From particle swarm optimization to consensus based optimization: Stochastic modeling and mean-field limit
Equation of State Calculations by Fast Computing Machines
Derivative-free optimization methods
On Pinsker's and Vajda's Type Inequalities for Csiszár's $f$-Divergences
Binary Interaction Algorithms for the Simulation of Flocking and Swarming Dynamics
A quest toward a mathematical theory of the dynamics of swarms
Monte Carlo sampling methods using Markov chains and their applications
Constrained Consensus-Based Optimization
Consensus‐based sampling
Consensus-based optimization via jump-diffusion stochastic differential equations
The grazing collisions limit from the linearized Boltzmann equation to the Landau equation for short-range potentials
On the Generalized Langevin Equation for Simulated Annealing
Kinetic-based optimization enhanced by genetic dynamics
On the global convergence of particle swarm optimization methods

This page was built for publication: Optimization by linear kinetic equations and mean-field Langevin dynamics

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6669902)