通过间接反馈优化目标函数，解决隐私与计算受限场景下的黑箱优化问题。
Indirect Query Bayesian Optimization with Integrated Feedback
- 基于条件期望构建间接查询框架，利用数据学习未知分布
- 提出CMES采集函数，在多分辨率反馈下实现高效搜索
- 适用于隐私保护、硬件受限等真实场景的优化任务
我们提出了间接查询贝叶斯优化（IQBO）框架，这是一种新型贝叶斯优化范式，其中对未知函数 $f$ 的优化目标通过其条件期望提供集成反馈。该条件分布可能未知，可从数据中学习。目标是通过自适应地在条件分布所定义的空间中查询与观测，找到 $f$ 的全局最优解。该方法源于现实应用中因隐私、硬件或计算限制无法获取直接反馈的问题。我们提出了条件最大值熵搜索（CMES）采集函数以应对这一新设定，并设计了具有多分辨率反馈的分层搜索算法以提升计算效率。我们给出了所提方法的后悔界，并在模拟优化任务中验证了其有效性。
原文摘要 · Abstract (English)
We develop the framework of Indirect Query Bayesian Optimization (IQBO), a new class of Bayesian optimization problems where the integrated feedback is given via a conditional expectation of the unknown function $f$ to be optimized. The underlying conditional distribution can be unknown and learned from data. The goal is to find the global optimum of $f$ by adaptively querying and observing in the space transformed by the conditional distribution. This is motivated by real-world applications where one cannot access direct feedback due to privacy, hardware or computational constraints. We propose the Conditional Max-Value Entropy Search (CMES) acquisition function to address this novel setting, and propose a hierarchical search algorithm with multi-resolution feedback to improve computational efficiency. We show regret bounds for our proposed methods and demonstrate the effectiveness of our approaches on simulated optimization tasks.
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。