多用户实时推荐中，用新模型提升点击率与效率。
Multi-User Contextual Cascading Bandits for Personalized Recommendation
- 基于序列曝光反馈与并行上下文，建模多用户同时交互
- 提出两种算法，理论证明其后悔上界分别达√(THN)与√(T+HN)
- 适合大规模个性化推荐系统，尤其高并发场景
我们提出多用户上下文级联强化学习（Multi-User Contextual Cascading Bandit, MCCB）模型，一种新的组合强化学习框架，用于刻画多个用户同时与顺序展示项目互动的在线广告场景。该框架整合三个核心结构：(i) 基于序列动作暴露的级联反馈机制；(ii) 支持选择性探索的并行上下文会话；(iii) 不同动作级别的异质奖励。首先提出上置信界带逆向规划（UCBBP）算法，适用于此设定，并证明其在T个回合、每回合H步会话、每回合N个上下文条件下，达到$ ilde{O}(igsqrt{THN})$的后悔上界。考虑到大量用户同时使用系统，进一步提出主动式上置信界带逆向规划（AUCBBP）算法，在上下文扩展（即用户扩展）方面实现严格效率提升，其后悔上界为$ ilde{O}(igsqrt{T+HN})$。通过数值实验验证了理论结果，表明两种算法在多种设置下均具有效果。
原文摘要 · Abstract (English)
We introduce a Multi-User Contextual Cascading Bandit model, a new combinatorial bandit framework that captures realistic online advertising scenarios where multiple users interact with sequentially displayed items simultaneously. Unlike classical contextual bandits, MCCB integrates three key structural elements: (i) cascading feedback based on sequential arm exposure, (ii) parallel context sessions enabling selective exploration, and (iii) heterogeneous arm-level rewards. We first propose Upper Confidence Bound with Backward Planning (UCBBP), a UCB-style algorithm tailored to this setting, and prove that it achieves a regret bound of $\widetilde{O}(\sqrt{THN})$ over $T$ episodes, $H$ session steps, and $N$ contexts per episode. Motivated by the fact that many users interact with the system simultaneously, we introduce a second algorithm, termed Active Upper Confidence Bound with Backward Planning (AUCBBP), which shows a strict efficiency improvement in context scaling, i.e., user scaling, with a regret bound of $\widetilde{O}(\sqrt{T+HN})$. We validate our theoretical findings via numerical experiments, demonstrating the empirical effectiveness of both algorithms under various settings.
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。