The performance of modern machine learning algorithms depends upon the selection of a set of hyperparameters. Common examples of hyperparameters are learning rate and the number of layers in a dense neural network. Auto-ML is a branch of optimization that has produced important contributions in this area. Within Auto-ML, hyperband-based approaches, which eliminate poorly-performing configurations after evaluating them at low budgets, are among the most effective. However, the performance of these algorithms strongly depends on how effectively they allocate the computational budget to various hyperparameter configurations. We present the new Parameter Optimization with Conscious Allocation (POCA), a hyperband-based algorithm that adaptively allocates the inputted budget to the hyperparameter configurations it generates following a Bayesian sampling scheme. We compare POCA to its nearest competitor at optimizing the hyperparameters of an artificial toy function and a deep neural network and find that POCA finds strong configurations faster in both settings.

现代机器学习算法的性能取决于一组超参数的选择。Auto-ML是优化的一个分支，在这一领域中，基于超带宽的方法是最有效的，而Parameter Optimization with Conscious Allocation (POCA)是一种自适应地将预算分配给超参数配置的超带宽算法，通过贝叶斯抽样方案生成的超参数配置更快地找到强配置。

意识分配参数优化 (POCA)