arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1209.5853cs.AI
收藏

有效的自然演化策略

Efficient Natural Evolution Strategies

IDSIA(达勒莫尔人工智能研究所)

Yi Sun, Daan Wierstra, Tom Schaul, Juergen Schmidhuber

摘要:

高效自然进化策略(Efficient Natural Evolution Strategies,eNES)是一种新的进化算法,它利用自然梯度来适应变异分布。与以前基于自然梯度的方法不同,eNES使用快速算法来计算精确Fisher信息矩阵的逆,从而提高其进化梯度估计的鲁棒性和性能,即使在更高的维度上。eNES的其他新方面包括最佳适应度基线和重要性混合(一种用很少的适应度评估更新种群的过程)。该算法在单峰和多峰基准上都产生了有竞争力的结果。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑