Theoretical Foundation for CMA-ES from Information Geometry Perspective
نویسندگان
چکیده
منابع مشابه
Alternative Restart Strategies for CMA-ES
This paper focuses on the restart strategy of CMA-ES on multi-modal functions. A first alternative strategy proceeds by decreasing the initial step-size of the mutation while doubling the population size at each restart. A second strategy adaptively allocates the computational budget among the restart settings in the BIPOP scheme. Both restart strategies are validated on the BBOB benchmark; the...
متن کاملBiometric Security from an Information-Theoretical Perspective
In this review, biometric systems are studied from an information theoretical point of view. In the first part biometric authentication systems are studied. The objective of these systems is, observing correlated enrollment and authentication biometric sequences, to generate or convey as large as possible secret keys by interchanging a public message, while minimizing privacy leakage. Here priv...
متن کاملInjecting External Solutions Into CMA-ES
This report considers how to inject external candidate solutions into the CMA-ES algorithm. The injected solutions might stem from a gradient or a Newton step, a surrogate model optimizer or any other oracle or search mechanism. They can also be the result of a repair mechanism, for example to render infeasible solutions feasible. Only small modifications to the CMA-ES are necessary to turn inj...
متن کاملGlobally Convergent Evolution Strategies and CMA-ES
In this paper we show how to modify a large class of evolution strategies (ES) to rigorously achieve a form of global convergence, meaning convergence to stationary points independently of the starting point. The type of ES under consideration recombine the parents by means of a weighted sum, around which the offsprings are computed by random generation. One relevant instance of such ES is CMA-...
متن کاملRecombination for Learning Strategy Parameters in the MO-CMA-ES
The multi-objective covariance matrix adaptation evolution strategy (MO-CMA-ES) is a variable-metric algorithm for real-valued vector optimization. It maintains a parent population of candidate solutions, which are varied by additive, zero-mean Gaussian mutations. Each individual learns its own covariance matrix for the mutation distribution considering only its parent and offspring. However, t...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Algorithmica
سال: 2011
ISSN: 0178-4617,1432-0541
DOI: 10.1007/s00453-011-9564-8