KL-based Control of the Learning Schedule for Surrogate Black-Box Optimization
This work addresses the efficiency of black-box optimization for practitioners in fields like engineering and machine learning, though it is incremental as it builds on existing surrogate optimization techniques.
The paper tackles the high sample complexity of the CMA-ES algorithm in black-box optimization by introducing a principled control for the learning schedule of surrogate models, based on Kullback-Leibler divergence, resulting in significant performance gains on ill-conditioned benchmark problems compared to state-of-the-art methods like BFGS.
This paper investigates the control of an ML component within the Covariance Matrix Adaptation Evolution Strategy (CMA-ES) devoted to black-box optimization. The known CMA-ES weakness is its sample complexity, the number of evaluations of the objective function needed to approximate the global optimum. This weakness is commonly addressed through surrogate optimization, learning an estimate of the objective function a.k.a. surrogate model, and replacing most evaluations of the true objective function with the (inexpensive) evaluation of the surrogate model. This paper presents a principled control of the learning schedule (when to relearn the surrogate model), based on the Kullback-Leibler divergence of the current search distribution and the training distribution of the former surrogate model. The experimental validation of the proposed approach shows significant performance gains on a comprehensive set of ill-conditioned benchmark problems, compared to the best state of the art including the quasi-Newton high-precision BFGS method.