arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1902.08285cs.LGstat.ML
收藏

黑箱优化问题的Bayes最优提前停止策略

Bayes Optimal Early Stopping Policies for Black-Box Optimization

Google Research(谷歌研究)

Matthew Streeter

摘要:

我们推导出一个最佳的政策,自适应重新启动的随机算法,根据观察到的功能运行到目前为止,以尽量减少所需的预期时间的算法成功终止。给定合适的贝叶斯先验,该结果可用于从包括随机搜索、连续减半和Hyperband的算法的大家族中选择最佳黑盒优化算法。在CIFAR-10和ImageNet超参数调整问题上,所提出的策略在达到给定目标准确度的预期时间方面比随机搜索提高了13倍,并且比基线自适应策略提高了3倍,只要其准确度低于中位数,就终止运行。

英文摘要:

We derive an optimal policy for adaptively restarting a randomized algorithm, based on observed features of the run-so-far, so as to minimize the expected time required for the algorithm to successfully terminate. Given a suitable Bayesian prior, this result can be used to select the optimal black-box optimization algorithm from among a large family of algorithms that includes random search, Successive Halving, and Hyperband. On CIFAR-10 and ImageNet hyperparameter tuning problems, the proposed policies offer up to a factor of 13 improvement over random search in terms of expected time to reach a given target accuracy, and up to a factor of 3 improvement over a baseline adaptive policy that terminates a run whenever its accuracy is below-median.

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。

↑