AI 中文总结
研究稳健重复上下文定价,设计出遗憾值为 \(\mathcal O(Cd + d^2\log T)\) 的算法,将腐败预算 \(C\) 与时间范围 \(T\) 的依赖分离,解决了前人遗留问题。
AI 中文摘要
我们研究稳健的重复上下文定价,其中估值线性依赖于特征。在每一轮 \(t\in[T]\),卖家观察一个上下文,发布一个价格,并仅收到可能被破坏的二元销售反馈。卖家知道被破坏轮数的上限 \(C\)。我们设计了一种遗憾值为 \(\mathcal O(Cd + d^2\log T)\) 的算法,其中 \(d\) 是上下文维度。这是稳健上下文定价的首个保证,将对腐败预算 \(C\) 的依赖与时间范围 \(T\) 分离,解决了Gupta等人(2025年)遗留的问题。
英文摘要
We study robust repeated contextual pricing, where valuations depends linearly on the features. At each round $t\in[T]$, a seller observes a context, posts a price, and receives only a possibly corrupted binary sale feedback. The seller knows an upper bound $C$ on the number of corrupted rounds. We design an algorithm with regret $\mathcal O(Cd+d^2\log T)$, where $d$ is the context dimension. This is the first guarantee for robust contextual pricing that separates the dependence on the corruption budget $C$ from the horizon $T$, closing the problem left open by Gupta, Guruganesh, Paes Leme, and Schneider (2025).