Stochastic consensus dynamics for nonconvex optimization on the Stiefel manifold: Mean-field limit and convergence

DOI10.1142/S0218202522500130zbMath1485.35361OpenAlexW4214514608MaRDI QIDQ5074805

Insoon Yang, Myeongju Kang, Seung-Yeal Ha, Jeong-Ho Kim, Dohyun Kim

Publication date: 10 May 2022

Published in: Mathematical Models and Methods in Applied Sciences (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1142/s0218202522500130

zbMATH Keywords

global optimizationFokker-Planck equationStiefel manifoldnonconvex optimizationconsensus-based optimization

Mathematics Subject Classification ID

Applications of stochastic analysis (to PDEs, etc.) (60H30) Stochastic methods (Fokker-Planck, Langevin, etc.) applied to problems in time-dependent statistical mechanics (82C31) PDEs in connection with control and optimization (35Q93) Mean field games and control (49N80)

Related Items (4)

Convergence analysis of the discrete consensus-based optimization algorithm with random batch interactions and heterogeneous noises ⋮ Consensus-based optimization via jump-diffusion stochastic differential equations ⋮ Collective behaviors of stochastic agent-based models and applications to finance and optimization ⋮ Ensemble-Based Gradient Inference for Particle Methods in Optimization and Sampling

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Mean-field limit for the stochastic Vicsek model
• Emergent dynamics of Cucker-Smale flocking particles in a random environment
• A framework of constraint preserving update schemes for optimization on Stiefel manifold
• Compact sets in the space \(L^ p(0,T;B)\)
• Applications of parametric programming and eigenvalue maximization to the quadratic assignment problem
• Particle and kinetic models for swarming particles on a sphere and stability properties
• A Procrustes problem on the Stiefel manifold
• On minimization on Stiefel manifolds
• Convergence and error estimates for time-discrete consensus-based optimization algorithms
• First order optimality conditions and steepest descent algorithm on orthogonal Stiefel manifolds
• A Riemannian conjugate gradient method for optimization on the Stiefel manifold
• On matrix exponentials and their approximations related to optimization on the Stiefel manifold
• Global optimization with orthogonality constraints via stochastic diffusion on manifold
• Nonconvex and nonsmooth optimization with generalized orthogonality constraints: an approximate augmented Lagrangian method
• A constrained optimization algorithm for total energy minimization in electronic structure calculations
• Ant colony optimization theory: a survey
• Stochastic evolutionary differential games toward a systems theory of behavioral social dynamics
• STOCHASTIC MEAN-FIELD LIMIT: NON-LIPSCHITZ FORCES AND SWARMING
• ON THE ASYMPTOTIC THEORY FROM MICROSCOPIC TO MACROSCOPIC GROWING TISSUE MODELS: AN OVERVIEW WITH PERSPECTIVES
• A consensus-based model for global optimization and its mean-field limit
• On the Modeling of Traffic and Crowds: A Survey of Models, Speculations, and Perspectives
• Convergence of a first-order consensus-based global optimization algorithm
• Consensus-based optimization on hypersurfaces: Well-posedness and mean-field limit
• Toward a mathematical theory of behavioral-social dynamics for pedestrian crowds
• The Geometry of Algorithms with Orthogonality Constraints
• Genetic Algorithms
• An analytical framework for consensus-based global optimization method
• A New First-Order Algorithmic Framework for Optimization Problems with Orthogonality Constraints
• Vehicular traffic, crowds, and swarms: From kinetic theory and multiscale methods to applications and research perspectives
• A consensus-based global optimization method for high dimensional machine learning problems
• Proximal Gradient Method for Nonsmooth Optimization over the Stiefel Manifold
• Optimal Transport

This page was built for publication: Stochastic consensus dynamics for nonconvex optimization on the Stiefel manifold: Mean-field limit and convergence