将强化学习中的探索算法用于超参优化，提升效率与准确性。
HyperArm Bandit Optimization: A Novel approach to Hyperparameter Optimization and an Analysis of Bandit Algorithms in Stochastic and Adversarial Settings
- 把每个超参数当作独立可调单元，动态分配资源进行搜索。
- 在分类与回归任务中，比贝叶斯优化更快更准。
- 适合需要快速迭代的机器学习系统开发人员。
本文研究了在随机与对抗性环境下使用多臂赌博机算法的理论分析与实际应用。首先介绍赌博机问题，区分随机与对抗性变体，并分析探索-再利用（ETC）、上置信界（UCB）及指数加权探索与利用算法（EXP3）等关键方法的理论后悔界。随后提出新型框架HyperArm Bandit Optimization（HABO），将EXP3应用于机器学习模型的超参数优化。不同于传统将完整配置视为一个动作的做法，HABO将单个超参数视为超臂，其可能取值作为子臂，实现动态资源分配与高效探索。实验表明，该方法在分类与回归任务中显著优于贝叶斯优化，在计算效率和准确率方面表现更优。论文还讨论了HABO的收敛性保证，展现了其在可扩展、鲁棒的超参数优化中的潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。