arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.01571cs.LGstat.ML
收藏

费用相关超参数的节俭优化

Frugal Optimization for Cost-related Hyperparameters

Microsoft Research(微软研究院)

Qingyun Wu, Chi Wang, Silu Huang

摘要:

对机器学习算法民主化的日益增长的需求要求低成本的超参数优化(HPO)解决方案。许多机器学习算法都有超参数,这可能会导致训练成本的大幅变化。但现有的HPO方法在很大程度上忽略了这一影响,无法在优化过程中适当地控制成本。为了解决这个问题,我们开发了一种新的成本节约的HPO解决方案。我们的解决方案的核心是一个简单的,但新的随机直接搜索方法,我们证明了收敛速度的$O(\frac{\sqrt{d}}{\sqrt{K}})$和$O(dε^{-2})$近似保证的总成本。我们提供了强有力的实证结果与国家的最先进的HPO方法在大型AutoML基准比较。

英文摘要:

The increasing demand for democratizing machine learning algorithms calls for hyperparameter optimization (HPO) solutions at low cost. Many machine learning algorithms have hyperparameters which can cause a large variation in the training cost. But this effect is largely ignored in existing HPO methods, which are incapable to properly control cost during the optimization process. To address this problem, we develop a new cost-frugal HPO solution. The core of our solution is a simple but new randomized direct-search method, for which we prove a convergence rate of $O(\frac{\sqrt{d}}{\sqrt{K}})$ and an $O(dε^{-2})$-approximation guarantee on the total cost. We provide strong empirical results in comparison with state-of-the-art HPO methods on large AutoML 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。

↑