71 citations · 368 across the 49 of their papers we have counts for
4 papers · 1 filter
Objective Improvement in Information-Geometric Optimization
Youhei Akimoto, Yann Ollivier
Information-Geometric Optimization (IGO) is a unified framework of stochastic algorithms for optimization problems. Given a family of probability distributions, IGO turns the origi…
Convergence of the Continuous Time Trajectories of Isotropic Evolution Strategies on Monotonic C^2-composite Functions
Youhei Akimoto, Anne Auger, Nikolaus Hansen
The Information-Geometric Optimization (IGO) has been introduced as a unified framework for stochastic search algorithms. Given a parametrized family of probability distributions o…
Theoretical foundation for CMA-ES from information geometric perspective
Youhei Akimoto, Yuichi Nagata, Isao Ono +1
This paper explores the theoretical basis of the covariance matrix adaptation evolution strategy (CMA-ES) from the information geometry viewpoint. To establish a theoretical founda…
Analysis of a Natural Gradient Algorithm on Monotonic Convex-Quadratic-Composite Functions
Youhei Akimoto
In this paper we investigate the convergence properties of a variant of the Covariance Matrix Adaptation Evolution Strategy (CMA-ES). Our study is based on the recent theoretical f…