非平稳自动出价世界中的在线广告采购
Online Ad Procurement in Non-stationary Autobidding Worlds
AI总结:
针对自动出价平台信息有限且采购结果非平稳的问题,本文提出带长期约束的在线学习原始-对偶算法,在多种未知数据生成过程下实现低遗憾。
摘要:
如今,在线广告主通过与自动出价平台互动来采购数字广告展示:广告主通过设置预算、目标投资回报率、最高每次点击成本等杠杆来传达高层采购目标。随后,广告平台代表广告主采购展示,并向广告主报告最终的采购转化(例如点击)。在实践中,广告主可能几乎无法获得平台采购细节的信息,而且采购结果会受到季节性模式、偶发系统损坏和市场趋势等非平稳因素影响,这使广告主难以有效优化杠杆决策。受此启发,我们提出一个在线学习框架,帮助广告主在采购结果非平稳的现实老虎机反馈环境中,在满足一般长期约束的同时动态优化广告平台杠杆决策。具体而言,我们引入一种原始-对偶算法,用于在多维决策变量、老虎机反馈和长期不确定约束下进行在线决策。我们证明,当采购结果分别由随机、对抗、对抗性损坏、周期性和遍历性过程生成时,无需知道哪一种过程是真实情况,我们的算法在多种世界中都能实现低遗憾。最后,我们强调,所提出的算法和理论结果可扩展到在线广告应用之外。
英文摘要:
Today's online advertisers procure digital ad impressions through interacting with autobidding platforms: advertisers convey high level procurement goals via setting levers such as budget, target return-on-investment, max cost per click, etc.. Then ads platforms subsequently procure impressions on advertisers' behalf, and report final procurement conversions (e.g. click) to advertisers. In practice, advertisers may receive minimal information on platforms' procurement details, and procurement outcomes are subject to non-stationary factors like seasonal patterns, occasional system corruptions, and market trends which make it difficult for advertisers to optimize lever decisions effectively. Motivated by this, we present an online learning framework that helps advertisers dynamically optimize ad platform lever decisions while subject to general long-term constraints in a realistic bandit feedback environment with non-stationary procurement outcomes. In particular, we introduce a primal-dual algorithm for online decision making with multi-dimension decision variables, bandit feedback and long-term uncertain constraints. We show that our algorithm achieves low regret in many worlds when procurement outcomes are generated through procedures that are stochastic, adversarial, adversarially corrupted, periodic, and ergodic, respectively, without having to know which procedure is the ground truth. Finally, we emphasize that our proposed algorithm and theoretical results extend beyond the applications of online advertising.
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。