arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.09440cs.LGstat.ML
收藏

广义线性上下文赌博机的在线连续超参数优化

Online Continuous Hyperparameter Optimization for Generalized Linear Contextual Bandits

University of California, Davis(加利福尼亚大学戴维斯分校);Google(谷歌公司);University of California, Los Angeles(加利福尼亚大学洛杉矶分校)

Yue Kang, Cho-Jui Hsieh, Thomas C. M. Lee

AI总结:

本文针对上下文赌博机超参数难以实时调优的问题,提出首个在线连续超参数调优框架 CDT,将超参数优化建模为非平稳连续臂赌博机,并设计 Zooming TS 算法,在理论和实验上均取得优于现有方法的效果。

摘要:

在随机上下文赌博机中,智能体根据过去经验从时间相关的动作集合中顺序做出动作,以最小化累积遗憾。与许多其他机器学习算法一样,赌博机的性能在很大程度上取决于超参数的取值,而理论上推导出的参数值在实践中可能导致不理想的结果。此外,在赌博机环境下,由于决策必须实时做出,使用交叉验证等离线调参方法来选择超参数是不可行的。为了应对这一挑战,我们提出了第一个用于上下文赌博机的在线连续超参数调优框架,以在实践中于搜索空间内实时学习最优参数配置。具体来说,我们使用名为 CDT(Continuous Dynamic Tuning,连续动态调优)的双层赌博机框架,并将超参数优化形式化为一个非平稳连续臂赌博机问题,其中每个臂代表一种超参数组合,对应的奖励是算法结果。对于顶层,我们提出了 Zooming TS 算法,该算法利用 Thompson Sampling(TS)进行探索,并采用重启技术来应对切换环境。所提出的 CDT 框架可以很容易地用于调优上下文赌博机算法,而无需为多个超参数预先指定候选集。我们进一步证明,该框架在理论上能够实现次线性遗憾,并且在合成数据集和真实数据集上始终优于所有现有方法。

英文摘要:

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 performance of bandits heavily depends on the values of hyperparameters, and theoretically derived parameter values may lead to unsatisfactory results in practice. Moreover, it is infeasible to use offline tuning methods like cross-validation to choose hyperparameters under the bandit environment, as the decisions should be made in real-time. To address this challenge, we propose the first online continuous hyperparameter tuning framework for contextual bandits to learn the optimal parameter configuration in practice within a search space on the fly. Specifically, we use a double-layer bandit framework named CDT (Continuous Dynamic Tuning) and formulate the hyperparameter optimization as a non-stationary continuum-armed bandit, where each arm represents a combination of hyperparameters, and the corresponding reward is the algorithmic result. For the top layer, we propose the Zooming TS algorithm that utilizes Thompson Sampling (TS) for exploration and a restart technique to get around the \textit{switching} environment. The proposed CDT framework can be easily utilized to tune contextual bandit algorithms without any pre-specified candidate set for multiple hyperparameters. We further show that it could achieve a sublinear regret in theory and performs consistently better than all existing methods on both synthetic and real datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑