HyperArm Bandit Optimization: A Novel approach to Hyperparameter Optimization and an Analysis of Bandit Algorithms in Stochastic and Adversarial Settings
This paper explores the application of bandit algorithms in both stochastic and adversarial settings, with a focus on theoretical analysis and practical applications. The study begins by introducing bandit problems, distinguishing between stochastic and adversarial variants, and examining key algorithms such as Explore-Then-Commit (ETC), Upper Confidence Bound (UCB), and Exponential-Weight Algorithm for Exploration and Exploitation (EXP3). Theoretical regret bounds are analyzed to compare the performance of these algorithms. The paper then introduces a novel framework, HyperArm Bandit Optimization (HABO), which applies EXP3 to hyperparameter tuning in machine learning models. Unlike traditional methods that treat entire configurations as arms, HABO treats individual hyperparameters as super-arms, and its potential configurations as sub-arms, enabling dynamic resource allocation and efficient exploration. Experimental results demonstrate HABO's effectiveness in classification and regression tasks, outperforming Bayesian Optimization in terms of computational efficiency and accuracy. The paper concludes with insights into the convergence guarantees of HABO and its potential for scalable and robust hyperparameter optimization.
Code (0)
등록된 구현이 없습니다.
Tasks
Bayesian OptimizationComputational EfficiencyEfficient ExplorationHyperparameter OptimizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Efficient Automatic CASH via Rising Bandits
The Combined Algorithm Selection and Hyperparameter optimization (CASH) is one of the most fundamental problems in Automatic Machine Learning (AutoML). The existing Bayesian optimization (BO) based solutions turn the CAS…
AutoMLBayesian OptimizationBIG-bench Machine LearningHyperparameter Optimization+1Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimization
Performance of machine learning algorithms depends critically on identifying a good set of hyperparameters. While recent approaches use Bayesian optimization to adaptively select configurations, we focus on speeding up r…
Bayesian OptimizationHyperparameter OptimizationAn Asymptotically Optimal Multi-Armed Bandit Algorithm and Hyperparameter Optimization
The evaluation of hyperparameters, neural architectures, or data augmentation policies becomes a critical model selection problem in advanced deep learning with a large hyperparameter search space. In this paper, we prop…
Bayesian OptimizationData AugmentationHyperparameter OptimizationModel Selection+4Online Continuous Hyperparameter Optimization for Generalized Linear Contextual Bandits
In stochastic contextual bandits, an agent sequentially makes actions from a time-dependent action set based on past experience to minimize the cumulative regret. Like many other machine learning algorithms, the performa…
Hyperparameter OptimizationMulti-Armed BanditsThompson SamplingBOHB: Robust and Efficient Hyperparameter Optimization at Scale
Modern deep learning methods are very sensitive to many hyperparameters, and, due to the long training times of state-of-the-art models, vanilla Bayesian hyperparameter optimization is typically computationally infeasibl…
Bayesian OptimizationDeep Reinforcement LearningHyperparameter OptimizationReinforcement Learning