自适应混合重要性采样用于自动化广告拍卖调优
Adaptive Mixture Importance Sampling for Automated Ads Auction Tuning
AI总结：
本文提出AMIS框架，通过动态调整混合分布参数及混合率优化大规模推荐系统KPI，实验证明其在噪声环境中优于传统GIS并能可靠识别最优调优点。
摘要：
本文引入了自适应混合重要性采样（AMIS）作为一种新方法，用于优化大规模推荐系统（如在线广告拍卖）中的关键性能指标（KPI）。传统重要性采样（IS）方法在动态环境中面临挑战，特别是在应对多模态景观的复杂性以及避免优化任务陷入局部最优方面。与经典的自适应IS和多重IS那样在迭代中更新重要性权重并混合样本不同，我们的AMIS框架利用混合分布作为提议分布，并在每次迭代中动态调整混合参数及其混合率，从而增强了搜索的多样性和效率。通过广泛的离线模拟，我们证明AMIS显著优于简单的高斯重要性采样（GIS），特别是在噪声环境中。此外，我们的方法通过在主要搜索引擎上进行在线A/B实验在真实场景中得到了验证，其中AMIS始终能够识别出更有可能被采纳为主流配置的最优调优点。这些发现表明，AMIS增强了噪声环境中的收敛性，从而在重要性采样离策略估计器的背景下实现更准确、更可靠的决策。
英文摘要：
This paper introduces Adaptive Mixture Importance Sampling (AMIS) as a novel approach for optimizing key performance indicators (KPIs) in large-scale recommender systems, such as online ad auctions. Traditional importance sampling (IS) methods face challenges in dynamic environments, particularly in navigating through complexities of multi-modal landscapes and avoiding entrapment in local optima for the optimization task. Instead of updating importance weights and mixing samples across iterations, as in canonical adaptive IS and multiple IS, our AMIS framework leverages a mixture distribution as the proposal distribution and dynamically adjusts both the mixture parameters and their mixing rates at each iteration, thereby enhancing search diversity and efficiency. Through extensive offline simulations, we demonstrate that AMIS significantly outperforms simple Gaussian Importance Sampling (GIS), particularly in noisy environments. Moreover, our approach is validated in real-world scenarios through online A/B experiments on a major search engine, where AMIS consistently identifies optimal tuning points that are more likely to be adopted as mainstream configurations. These findings indicate that AMIS enhances convergence in noisy environments, leading to more accurate and reliable decision-making in the context of importance sampling off-policy estimators.
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。
