On the adaptation of noise level for stochastic optimization

This paper deals with the optimization of noisy fitness functions, where the noise level can be reduced by increasing the computational effort. We theoretically investigate the question of the control of the noise level. We analyse two different schemes for an adaptive control and prove sufficient conditions ensuring the existence of an homogeneous Markov chain, which is the first step to prove linear convergence when dealing with non-noisy fitness functions. We experimentally validate the relevance of the homogeneity criterion. Large-scale experiments conclude to the efficiency in a difficult framework.