Information-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles
From MaRDI portal
Publication:5361281
zbMath1433.90196arXiv1106.3708MaRDI QIDQ5361281
Nikolaus Hansen, Anne Auger, Ludovic Arnold, Yann Ollivier
Publication date: 27 September 2017
Full work available at URL: https://arxiv.org/abs/1106.3708
stochastic optimizationinvariancenatural gradientrandomized optimizationblack-box optimizationevolution strategyinformation-geometric optimization
Parametric inference (62F99) Derivative-free methods and methods using generalized derivatives (90C56) Stochastic programming (90C15)
Related Items (17)
Natural gradient flow in the mixture geometry of a discrete exponential family ⋮ Principled Design of Continuous Stochastic Search: From Theory to Practice ⋮ Linear Convergence of Comparison-based Step-size Adaptive Randomized Search via Stability of Markov Chains ⋮ Information geometry of physics-informed statistical manifolds and its use in data assimilation ⋮ Unnamed Item ⋮ Global linear convergence of evolution strategies with recombination on scaling-invariant functions ⋮ Entropic Trust Region for Densest Crystallographic Symmetry Group Packings ⋮ Analysis of surrogate-assisted information-geometric optimization algorithms ⋮ Riemannian Natural Gradient Methods ⋮ Verifiable conditions for the irreducibility and aperiodicity of Markov chains by analyzing underlying deterministic models ⋮ Optimal transport natural gradient for statistical manifolds with continuous sample space ⋮ Online natural gradient as a Kalman filter ⋮ Warped Riemannian Metrics for Location-Scale Models ⋮ Global Sensitivity Analysis for Optimization with Variable Selection ⋮ An ODE method to prove the geometric convergence of adaptive stochastic algorithms ⋮ Unnamed Item ⋮ Laplace approximation and natural gradient for Gaussian process regression with heteroscedastic Student-\(t\) model
This page was built for publication: Information-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles
