Epsilon-Lexicase Selection for Regression
Epsilon-Lexicase Selection for Regression
复制标题
用于回归的 Epsilon-Lexicase 选择
DOI：
--
复制
发表时间：
2016
期刊：
影响因子：
--
通讯作者：
K. Danai
中科院分区：
文献类型：
--
作者：
W. L. Cava;L. Spector;K. Danai
Lexicase 选择是一种父选择方法，在执行父选择时，它会单独而不是聚合地考虑测试用例。它在离散误差空间中表现良好，但在构成大多数系统识别任务的连续值问题上表现不佳。在本文中，我们开发了一种用于符号回归的新形式的词汇选择，称为ε-词汇选择，它以更有效的方式重新定义了每个测试用例中个体的通过条件。我们对 ε 的几种处理方法对现实世界和综合问题进行了一系列实验，并量化了 ε 如何影响亲本选择和模型性能。 ε-词典选择被证明对回归有效，与锦标赛选择和年龄适应帕累托优化等其他技术相比，可以产生更好的拟合模型。我们证明，ε 可以根据总体性能分布自动适应各个测试用例。我们的实验表明，使用自动 ε 进行 ε-lexicase 选择可以在测试问题中生成最准确的模型，而计算开销可以忽略不计。我们表明，在词典选择处理中，行为多样性异常高，并且 ε-词典选择在选择父母时比词典选择使用更多的适应度案例，这有助于解释性能的提高。
Lexicase selection is a parent selection method that considers test cases separately, rather than in aggregate, when performing parent selection. It performs well in discrete error spaces but not on the continuous-valued problems that compose most system identification tasks. In this paper, we develop a new form of lexicase selection for symbolic regression, named ε-lexicase selection, that redefines the pass condition for individuals on each test case in a more effective way. We run a series of experiments on real-world and synthetic problems with several treatments of ε and quantify how ε affects parent selection and model performance. ε-lexicase selection is shown to be effective for regression, producing better fit models compared to other techniques such as tournament selection and age-fitness Pareto optimization. We demonstrate that ε can be adapted automatically for individual test cases based on the population performance distribution. Our experiments show that ε-lexicase selection with automatic ε produces the most accurate models across tested problems with negligible computational overhead. We show that behavioral diversity is exceptionally high in lexicase selection treatments, and that ε-lexicase selection makes use of more fitness cases when selecting parents than lexicase selection, which helps explain the performance improvement.
DOI：
10.1007/bfb0055923
发表时间：
1998
期刊：
--
影响因子：
--
作者：
Moshe Sipper
通讯作者：
Moshe Sipper