arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1502.07943cs.LGstat.ML
收藏

非随机最佳臂辨识与超参数优化

Non-stochastic Best Arm Identification and Hyperparameter Optimization

University of Wisconsin(威斯康星大学);UCLA(加州大学洛杉矶分校)

Kevin Jamieson, Ameet Talwalkar

摘要:

受超参数优化任务的启发,我们引入了非随机最佳臂辨识问题。在多臂强盗文献中,累积后悔目标在非随机和随机环境下都有算法和分析,而据我们所知,最佳臂识别框架仅在随机环境下被考虑。我们在这个框架下引入非随机设置,确定一个已知的算法,非常适合这种设置,并分析其行为。接下来,通过利用标准机器学习算法的迭代性质,我们将超参数优化作为非随机最佳臂识别的实例,并根据经验评估我们提出的算法。我们的实证结果表明,通过分配更多的资源,有前途的超参数设置,我们通常实现可比的测试精度比基线方法快一个数量级。

英文摘要:

Motivated by the task of hyperparameter optimization, we introduce the non-stochastic best-arm identification problem. Within the multi-armed bandit literature, the cumulative regret objective enjoys algorithms and analyses for both the non-stochastic and stochastic settings while to the best of our knowledge, the best-arm identification framework has only been considered in the stochastic setting. We introduce the non-stochastic setting under this framework, identify a known algorithm that is well-suited for this setting, and analyze its behavior. Next, by leveraging the iterative nature of standard machine learning algorithms, we cast hyperparameter optimization as an instance of non-stochastic best-arm identification, and empirically evaluate our proposed algorithm on this task. Our empirical results show that, by allocating more resources to promising hyperparameter settings, we typically achieve comparable test accuracies an order of magnitude faster than baseline methods.

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。

↑