My search problem is essentially sphere with a noisy evaluation. This noise is causing CMA-ES to converge at a ridiculously slow rate. Is there any way to force CMA-ES to converge in an approximate manner in the face of noise?
Note: I don't need convergence to the exact optimum as I can fine tune that later, so I'm looking for a fast convergence to the near optimum (in a unimodal, but noisy search space).