We propose the ChaCha (Champion-Challengers) algorithm for making an online choice of hyperparameters in online learning settings. ChaCha handles the process of determining a champion and scheduling a set of `live' challengers over time based on sample complexity bounds. It is guaranteed to have sublinear regret after the optimal configuration is added into consideration by an application-dependent oracle based on the champions. Empirically, we show that ChaCha provides good performance across a wide array of datasets when optimizing over featurization and hyperparameter decisions.

翻译：我们提出Chacha(Champion-Challengers)算法,用于在线选择在线学习环境中的超参数。Chacha根据样本复杂度,处理确定冠军的过程,并安排一组“实时”挑战者,在一段时间内根据样本复杂度进行定时。在以冠军为根据的以应用程序为依存的甲骨文来考虑最佳配置后,可以保证出现亚线性遗憾。我们很生动地表明,Chacha在优化超生化和超常参数决定时,在一系列广泛的数据集中提供良好的性能。