output
20112021
most citedCOCO: A Platform for Comparing Continuous Optimizers in a Black-Box Setting

406 citations

5 papers

math.OC2021

Global linear convergence of Evolution Strategies with recombination on scaling-invariant functions

Cheikh Touré, Anne Auger, Nikolaus Hansen

Evolution Strategies (ES) are stochastic derivative-free optimization algorithms whose most prominent representative, the CMA-ES algorithm, is widely used to solve difficult numeri…

math.OC2021

Scaling-invariant functions versus positively homogeneous functions

Cheikh Touré, Armand Gissler, Anne Auger +1

Scaling-invariant functions preserve the order of points when the points are scaled by the same positive scalar (with respect to a unique reference point). Composites of strictly m…

cs.AI2016★ 406 cited

COCO: A Platform for Comparing Continuous Optimizers in a Black-Box Setting

Nikolaus Hansen, Anne Auger, Raymond Ros +3

We introduce COCO, an open source platform for Comparing Continuous Optimizers in a black-box setting. COCO aims at automatizing the tedious and repetitive task of benchmarking num…

math.PR2015★ 10 cited

Verifiable Conditions for the Irreducibility and Aperiodicity of Markov Chains by Analyzing Underlying Deterministic Models

Alexandre Chotard, Anne Auger

We consider Markov chains that obey the following general non-linear state space model: where the function is while is typically d…

math.OC2011★ 205 cited

Information-Geometric Optimization Algorithms: A Unifying Picture via Invariance Principles

Yann Ollivier, Ludovic Arnold, Anne Auger +1

We present a canonical way to turn any smooth parametric family of probability distributions on an arbitrary search space into a continuous-time black-box optimization method o…