论文标题
ACE：自适应约束意识早在超参数优化中停止
ACE: Adaptive Constraint-aware Early Stopping in Hyperparameter Optimization
论文作者
论文摘要
部署机器学习模型需要高模型质量，并且需要遵守应用程序限制。这激发了超参数优化（HPO），以调整部署约束下的模型配置。这些约束通常需要额外的计算成本来评估，而训练不合格的配置可能会浪费大量的调整成本。在这项工作中，我们提出了一种自适应约束 - 感知的早期停止方法（ACE）方法，将约束评估纳入HPO期间的试验修剪。为了最大程度地降低整体优化成本，ACE根据对预期评估成本的理论分析估算了成本效益的约束评估间隔。同时，我们在ACE中提出了一个早期停止标准的层，该标准在修剪中考虑了优化和约束指标，并且不需要正则化超标剂。我们的实验表明，在公平或鲁棒性约束下，ACE在分类任务的高参数调整中的出色表现。
Deploying machine learning models requires high model quality and needs to comply with application constraints. That motivates hyperparameter optimization (HPO) to tune model configurations under deployment constraints. The constraints often require additional computation cost to evaluate, and training ineligible configurations can waste a large amount of tuning cost. In this work, we propose an Adaptive Constraint-aware Early stopping (ACE) method to incorporate constraint evaluation into trial pruning during HPO. To minimize the overall optimization cost, ACE estimates the cost-effective constraint evaluation interval based on a theoretical analysis of the expected evaluation cost. Meanwhile, we propose a stratum early stopping criterion in ACE, which considers both optimization and constraint metrics in pruning and does not require regularization hyperparameters. Our experiments demonstrate superior performance of ACE in hyperparameter tuning of classification tasks under fairness or robustness constraints.
