Non-stochastic Best Arm Identification and Hyperparameter Optimization

Abstract

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.

References in corpus (5)

• Scikit-learn: Machine Learning in Python
• lil' UCB : An Optimal Exploration Algorithm for Multi-Armed Bandits
• Freeze-Thaw Bayesian Optimization
• TuPAQ: An Efficient Planner for Large-scale Predictive Analytic Queries
• Oracle inequalities for computationally adaptive model selection

Cited by in corpus (19)

• Train faster, generalize better: Stability of stochastic gradient descent
• Automated Machine Learning in Practice: State of the Art and Recent Results
• Stochastic analysis of heterogeneous porous material with modified neural architecture search (NAS) based physics-informed neural networks using transfer learning
• Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
• Towards Green Automated Machine Learning: Status Quo and Future Directions
• Learning the Effect of Registration Hyperparameters with HyperMorph
• Learning Curves for Decision Making in Supervised Machine Learning: A Survey
• A Multi-Phase Approach for Product Hierarchy Forecasting in Supply Chain Management: Application to MonarchFx Inc
• Efficient Automatic CASH via Rising Bandits
• Review of the state of the art in autonomous artificial intelligence
• Promoting Fairness through Hyperparameter Optimization
• Can Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML
• Using Supervised Deep-Learning to Model Edge-FBG Shape Sensors
• Black-Box Optimization in Machine Learning with Trust Region Based Derivative Free Algorithm
• TUNA: Tuning Unstable and Noisy Cloud Applications
• Transfer Learning based Search Space Design for Hyperparameter Tuning
• Transformation-Interaction-Rational Representation for Symbolic Regression
• Paramater Optimization for Manipulator Motion Planning using a Novel Benchmark Set
• Greedy methods, randomization approaches and multi-arm bandit algorithms for efficient sparsity-constrained optimization