Global linear convergence of evolution strategies with recombination on scaling-invariant functions
DOI10.1007/s10898-022-01249-6zbMath1518.90108arXiv2107.08847OpenAlexW3184100370MaRDI QIDQ6102180
Cheikh Toure, Anne Auger, Nikolaus Hansen
Publication date: 8 May 2023
Published in: Journal of Global Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2107.08847
linear convergenceevolution strategiesCMA-ESFoster-Lyapunov drift conditionsscaling-invariant functions
Nonlinear programming (90C30) Derivative-free methods and methods using generalized derivatives (90C56) Approximation methods and heuristics in mathematical programming (90C59)
Related Items (1)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Globally convergent evolution strategies
- Markov chains and stochastic stability
- Differential evolution. In search of solutions.
- Efficient covariance matrix update for variable metric evolution strategies
- Differential evolution -- a simple and efficient heuristic for global optimization over continuous spaces
- Global convergence for evolution strategies in spherical problems: Some simple proofs and difficulties.
- Verifiable conditions for the irreducibility and aperiodicity of Markov chains by analyzing underlying deterministic models
- Learning probability distributions in continuous evolutionary algorithms -- a comparative review
- Convergence results for the (1,\(\lambda\))-SA-ES using the theory of \(\varphi\)-irreducible Markov chains
- Theoretical foundation for CMA-ES from information geometry perspective
- An ODE method to prove the geometric convergence of adaptive stochastic algorithms
- Algorithmic analysis of a basic evolutionary algorithm for continuous optimization
- Derivative-free optimization: a review of algorithms and comparison of software implementations
- Weighted multirecombination evolution strategies
- How the (1+1) ES using isotropic mutations minimizes positive definite quadratic forms
- Scaling-invariant functions versus positively homogeneous functions
- ON THE LAW OF LARGE NUMBERS FOR (GEOMETRICALLY) ERGODIC MARKOV CHAINS
- Linear Convergence of Comparison-based Step-size Adaptive Randomized Search via Stability of Markov Chains
- Principled Design of Continuous Stochastic Search: From Theory to Practice
- The existence of moments for stationary Markov chains
- Global Linear Convergence of Evolution Strategies on More than Smooth Strongly Convex Functions
- Asymptotic Behavior of Stochastic Systems Possessing Markovian Realizations
- Generalized drift analysis in continuous domain
- Information-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles
- Foundations of Genetic Algorithms
- Foundations of Genetic Algorithms
This page was built for publication: Global linear convergence of evolution strategies with recombination on scaling-invariant functions
