Non-stochastic Best Arm Identification and Hyperparameter Optimization
This work addresses hyperparameter optimization for machine learning practitioners, offering a more efficient method that is incremental in extending best-arm identification to non-stochastic settings.
The paper tackles the problem of hyperparameter optimization by introducing a non-stochastic best-arm identification framework, which is novel in the multi-armed bandit literature. Empirical results show that their proposed algorithm achieves comparable test accuracies an order of magnitude faster than baseline methods.
Motivated by the task of hyperparameter optimization, we introduce the non-stochastic best-arm identification problem. Within the multi-armed bandit literature, the cumulative regret objective enjoys algorithms and analyses for both the non-stochastic and stochastic settings while to the best of our knowledge, the best-arm identification framework has only been considered in the stochastic setting. We introduce the non-stochastic setting under this framework, identify a known algorithm that is well-suited for this setting, and analyze its behavior. Next, by leveraging the iterative nature of standard machine learning algorithms, we cast hyperparameter optimization as an instance of non-stochastic best-arm identification, and empirically evaluate our proposed algorithm on this task. Our empirical results show that, by allocating more resources to promising hyperparameter settings, we typically achieve comparable test accuracies an order of magnitude faster than baseline methods.