Binary interaction methods for high dimensional global optimization and machine learning

DOI10.1007/s00245-022-09836-5zbMath1489.90132arXiv2105.02695OpenAlexW3158645870MaRDI QIDQ2152587

Giacomo Borghi, Lorenzo Pareschi, Alessandro Benfenati

Publication date: 8 July 2022

Published in: Applied Mathematics and Optimization (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2105.02695

zbMATH Keywords

global optimizationBoltzmann equationmachine learningmean-field limitgradient-free methodsconsensus-based optimization

Mathematics Subject Classification ID

Monte Carlo methods (65C05) Nonconvex programming, global optimization (90C26) Derivative-free methods and methods using generalized derivatives (90C56) Learning and adaptive systems in artificial intelligence (68T05) Approximation methods and heuristics in mathematical programming (90C59) Kinetic theory of gases in time-dependent statistical mechanics (82C40)

Related Items

Constrained Consensus-Based Optimization ⋮ Reproducing kernel Hilbert spaces in the mean field limit ⋮ Consensus-based optimization via jump-diffusion stochastic differential equations ⋮ Kinetic-based optimization enhanced by genetic dynamics ⋮ An adaptive consensus based method for multi-objective optimization with uniform Pareto front approximation ⋮ Unnamed Item

Uses Software

• PRMLT

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Optimization by Simulated Annealing
• A literature survey of benchmark functions for global optimisation problems
• Modeling opinion formation in the kinetic theory of active particles. I: Spontaneous trend
• Opinion dynamics over complex networks: kinetic modelling and numerical methods
• Mean field models for large data-clustering problems
• Large deviations techniques and applications.
• Simulated annealing via Sobolev inequalities
• The Boltzmann equation and its applications
• The mathematical theory of dilute gases
• Mean field control hierarchy
• A note on the mean-field limit for the particle swarm optimization
• Consensus-based global optimization with personal best
• Random batch methods (RBM) for interacting particle systems
• Nonlinear microscale interactions in the kinetic theory of active particles
• Ant colony optimization theory: a survey
• A short discussion is followed by an agreement on the global minimum: consensus-based global optimization
• An introduction to Monte Carlo method for the Boltzmann equation
• A consensus-based model for global optimization and its mean-field limit
• Consensus-based optimization on hypersurfaces: Well-posedness and mean-field limit
• An analytical framework for consensus-based global optimization method
• A consensus-based global optimization method for high dimensional machine learning problems
• Uniform error estimates for the random batch method to the first‐order consensus models with antisymmetric interaction kernels
• A Consensus-Based Global Optimization Method with Adaptive Momentum Estimation
• From particle swarm optimization to consensus based optimization: Stochastic modeling and mean-field limit
• Binary Interaction Algorithms for the Simulation of Flocking and Swarming Dynamics
• Monte Carlo sampling methods using Markov chains and their applications
• Direct Simulation and the Boltzmann Equation
• A Simplex Method for Function Minimization
• Handbook of metaheuristics