校准问题：解决大规模广告推荐系统中的最大化偏差
Calibration Matters: Tackling Maximization Bias in Large-scale Advertising Recommendation Systems
摘要：
校准定义为平均预测点击率与真实点击率的比率。定标的优化对于许多在线广告推荐系统来说是必不可少的，因为它直接影响到广告拍卖中下游的出价以及向广告主收取的金额。尽管其重要性，校准优化往往遭受一个问题称为“最大化偏差”。最大化偏倚是指预测值的最大值高估真实最大值的现象。引入该问题是因为校准是在由预测模型本身选择的集合上计算的。即使在训练集和测试集之间存在协变量偏移时，可以在每个数据点上实现无偏预测，它也仍然存在。为了缓解这个问题，我们理论化的最大化偏差的量化，并提出了方差调整去偏置（VAD）在本文中的元算法。该算法是有效的，强大的，和实用的，因为它是能够减轻最大化偏差问题下的协变量偏移，既不产生额外的在线服务成本，也不损害排名性能。我们证明了所提出的算法的有效性，使用一个国家的最先进的推荐神经网络模型的大规模现实世界的数据集。
英文摘要：
Calibration is defined as the ratio of the average predicted click rate to the true click rate. The optimization of calibration is essential to many online advertising recommendation systems because it directly affects the downstream bids in ads auctions and the amount of money charged to advertisers. Despite its importance, calibration optimization often suffers from a problem called "maximization bias". Maximization bias refers to the phenomenon that the maximum of predicted values overestimates the true maximum. The problem is introduced because the calibration is computed on the set selected by the prediction model itself. It persists even if unbiased predictions can be achieved on every datapoint and worsens when covariate shifts exist between the training and test sets. To mitigate this problem, we theorize the quantification of maximization bias and propose a variance-adjusting debiasing (VAD) meta-algorithm in this paper. The algorithm is efficient, robust, and practical as it is able to mitigate maximization bias problems under covariate shifts, neither incurring additional online serving costs nor compromising the ranking performance. We demonstrate the effectiveness of the proposed algorithm using a state-of-the-art recommendation neural network model on a large-scale real-world dataset.
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。
