The Canonical Evolutionary Strategy converges globally by spectral concentration on the principal eigenfunction of a replicator-mutator operator, explaining survival of the flattest.
Consensus-based optimization for closed-box adversarial attacks and a connection to evolution strategies
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
unclear 1representative citing papers
A stochastic particle system is proposed in Hilbert spaces with associated mean-field limit, establishing well-posedness, consensus analysis, and convergence to the minimizer under suitable assumptions on the objective, plus a finite-particle algorithm.
Establishes exponential convergence in Wasserstein distance for the mean-field limit and finite-particle approximation of a consensus-based method solving nonconvex bi-level optimization problems.
citing papers explorer
-
From Mean-Field Limits to Semiclassical Concentration: Global Convergence of the Canonical Evolutionary Strategy
The Canonical Evolutionary Strategy converges globally by spectral concentration on the principal eigenfunction of a replicator-mutator operator, explaining survival of the flattest.
-
A derivative-free particle method for optimization in Hilbert spaces
A stochastic particle system is proposed in Hilbert spaces with associated mean-field limit, establishing well-posedness, consensus analysis, and convergence to the minimizer under suitable assumptions on the objective, plus a finite-particle algorithm.
-
Convergence of Consensus-Based Particle Methods for Nonconvex Bi-Level Optimization
Establishes exponential convergence in Wasserstein distance for the mean-field limit and finite-particle approximation of a consensus-based method solving nonconvex bi-level optimization problems.