Recommender systems (RS) aim to retrieve a small set of items that best match individual user preferences. Naturally, RS place primary emphasis on the quality of the Top-$K$ results rather than performance across the entire item set. However, estimating Top-$K$ accuracy (e.g., Precision@$K$, Recall@$K$) requires determining the ranking positions of items, which imposes substantial computational overhead and poses significant challenges for optimization. In addition, RS often suffer from distribution shifts due to evolving user preferences or data biases, further complicating the task. To address these issues, we propose Talos, a loss function that is specifically designed to optimize the Talos recommendation accuracy. Talos leverages a quantile technique that replaces the complex ranking-dependent operations into simpler comparisons between predicted scores and learned score thresholds. We further develop a sampling-based regression algorithm for efficient and accurate threshold estimation, and introduce a constraint term to maintain optimization stability by preventing score inflation. Additionally, we incorporate a tailored surrogate function to address discontinuity and enhance robustness against distribution shifts. Comprehensive theoretical analyzes and empirical experiments are conducted to demonstrate the effectiveness, efficiency, convergence, and distributional robustness of Talos. The code is available at https://github.com/cynthia-shengjia/WWW-2026-Talos.

翻译：推荐系统（RS）旨在检索与用户个人偏好最匹配的小规模物品集合。自然地，推荐系统主要关注Top-$K$结果的质量，而非在整个物品集上的整体表现。然而，估计Top-$K$准确率（如Precision@$K$、Recall@$K$）需要确定物品的排序位置，这带来了巨大的计算开销，并为优化带来了显著挑战。此外，推荐系统常因用户偏好演变或数据偏差而遭受分布偏移，进一步使任务复杂化。为解决这些问题，我们提出了Talos，一种专门为优化Top-$K$推荐准确率而设计的损失函数。Talos利用分位数技术，将复杂的依赖排序的操作替换为预测分数与学习到的分数阈值之间的简单比较。我们进一步开发了一种基于采样的回归算法，以实现高效且准确的阈值估计，并引入一个约束项，通过防止分数膨胀来保持优化稳定性。此外，我们结合了一个定制的代理函数，以解决不连续性问题并增强对分布偏移的鲁棒性。我们进行了全面的理论分析和实证实验，以证明Talos的有效性、效率、收敛性以及分布鲁棒性。代码可在https://github.com/cynthia-shengjia/WWW-2026-Talos获取。