Hyperparameter tuning is a common technique for improving the performance of neural networks. Most techniques for hyperparameter search involve an iterated process where the model is retrained at every iteration. However, the expected accuracy improvement from every additional search iteration, is still unknown. Calculating the expected improvement can help create stopping rules for hyperparameter tuning and allow for a wiser allocation of a project's computational budget. In this paper, we establish an empirical estimate for the expected accuracy improvement from an additional iteration of hyperparameter search. Our results hold for any hyperparameter tuning method which is based on random search \cite{bergstra2012random} and samples hyperparameters from a fixed distribution. We bound our estimate with an error of $O\left(\sqrt{\frac{\log k}{k}}\right)$ w.h.p. where $k$ is the current number of iterations. To the best of our knowledge this is the first bound on the expected gain from an additional iteration of hyperparameter search. Finally, we demonstrate that the optimal estimate for the expected accuracy will still have an error of $\frac{1}{k}$.
翻译:超光谱调试是改善神经网络性能的一种常见技术。 多数超光谱搜索技术都涉及一个迭代过程, 该模型在每次迭代中都经过再培训。 然而, 每一个额外的搜索迭代的预期精确度提高仍然未知。 计算预期改进有助于为超光谱调试创建停止规则, 并允许更明智地分配项目的计算预算。 在本文中, 我们为从超光谱搜索增加的迭代中预期的准确性提高制定了一个经验性估算。 我们的结果是, 任何基于随机搜索\ cite{ bergstra2012dom} 的超光谱调控方法, 以及从固定分布的样本中提取超参数。 我们用一个错误的 $left (sqrtrt\frac k ⁇ käk ⁇ right) w. h. h. p. 来约束我们的估计数。 $k$k$@ kright) 是当前电路数。 据我们所知, 这是预期从超光谱搜索中获取的收益的第一个约束。 最后, 我们证明, $1\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\