提出新贝叶斯算法，实现在线模型选择并逼近最优基学习器表现。
Bayesian Online Model Selection
- 基于贝叶斯框架设计自适应探索策略，动态选择最优基学习器。
- 理论证明贝叶斯后悔上界为 $O(d^* M oot{T} + oot{MT})$，性能逼近最优。
- 实验证明可媲美最佳基学习器，且共享数据能缓解先验误设问题。
在贝叶斯老虎机中进行在线模型选择面临根本性探索挑战：当环境实例来自先验分布时，如何设计一种自适应策略，以探索多个老虎机学习器，并在事后与最优者竞争？本文提出一种新的贝叶斯算法，用于随机老虎机中的在线模型选择。我们证明了贝叶斯后悔的“预言式”上界为 $O(d^* M oot{T} + oot{MT})$，其中 $M$ 为基学习器数量，$d^*$ 为最优基学习器的后悔系数，$T$ 为时间范围。我们在多种随机老虎机设置下进行了实证验证，结果表明该方法性能可媲美最优基学习器。此外，我们研究了基学习器间共享数据的影响，发现其有助于缓解先验误设问题。
原文摘要 · Abstract (English)
Online model selection in Bayesian bandits raises a fundamental exploration challenge: When an environment instance is sampled from a prior distribution, how can we design an adaptive strategy that explores multiple bandit learners and competes with the best one in hindsight? We address this problem by introducing a new Bayesian algorithm for online model selection in stochastic bandits. We prove an oracle-style guarantee of $O\left( d^* M \sqrt{T} + \sqrt{(MT)} \right)$ on the Bayesian regret, where $M$ is the number of base learners, $d^*$ is the regret coefficient of the optimal base learner, and $T$ is the time horizon. We also validate our method empirically across a range of stochastic bandit settings, demonstrating performance that is competitive with the best base learner. Additionally, we study the effect of sharing data among base learners and its role in mitigating prior mis-specification.
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。