Efficient Natural Evolution Strategies
This work addresses the challenge of efficient and robust optimization in evolutionary computation, particularly for researchers and practitioners in machine learning and optimization, though it appears incremental as it builds on existing natural gradient methods.
The paper tackles the problem of improving evolutionary algorithms by introducing Efficient Natural Evolution Strategies (eNES), which uses a fast algorithm to compute the inverse Fisher information matrix for natural gradient adaptation, resulting in increased robustness and performance, with competitive results on unimodal and multimodal benchmarks.
Efficient Natural Evolution Strategies (eNES) is a novel alternative to conventional evolutionary algorithms, using the natural gradient to adapt the mutation distribution. Unlike previous methods based on natural gradients, eNES uses a fast algorithm to calculate the inverse of the exact Fisher information matrix, thus increasing both robustness and performance of its evolution gradient estimation, even in higher dimensions. Additional novel aspects of eNES include optimal fitness baselines and importance mixing (a procedure for updating the population with very few fitness evaluations). The algorithm yields competitive results on both unimodal and multimodal benchmarks.