学习在上下文第一价格拍卖中出价
Learning to Bid in Contextual First Price Auctions
摘要:
本文研究了重复上下文第一价格拍卖中的投标问题。我们考虑一个单一的投标人(学习者)谁反复出价在第一价格拍卖:在每一次$t$,学习者观察上下文$x_t\in \mathbb{R}^d$,并决定出价的基础上的历史信息和$x_t$。我们假设所有其他$m_t = α_0\cdot x_t + z_t$的最大出价的结构化线性模型,其中$α_0\in \mathbb{R}^d$对于学习者是未知的,并且$z_t$从具有对数凹密度函数$f$的噪声分布$\mathcal{F}$中随机采样。在每次$t$结束时,我们考虑\emph{binary feedback}(学习者只能观察她是否获胜)和\emph{full information feedback}(学习者可以观察$m_t$)。对于二进制反馈,当噪声分布$\mathcal{F}$已知时,提出了一种竞价算法,利用最大似然估计(MLE)方法实现最多$\widetilde{O}(\sqrt{\log(d) T})$后悔.此外,我们推广该算法的设置与二进制反馈和噪声分布是未知的,但属于一个参数化的家庭的分布。对于\emph{unknown}噪声分布的完全信息反馈,我们给出了一个最多达到$\widetilde{O}(\sqrt{dT})$的后悔算法.我们的方法结合了对数凹密度函数的估计,然后MLE方法学习噪声分布$\mathcal{F}$和线性权重$α_0$同时。我们还提供了一个下界的结果,使得任何投标政策在一个广泛的类必须实现遗憾至少$Ω(\sqrt{T})$,即使当学习者收到完整的信息反馈和$\mathcal{F}$是已知的。
英文摘要:
In this paper, we investigate the problem about how to bid in repeated contextual first price auctions. We consider a single bidder (learner) who repeatedly bids in the first price auctions: at each time $t$, the learner observes a context $x_t\in \mathbb{R}^d$ and decides the bid based on historical information and $x_t$. We assume a structured linear model of the maximum bid of all the others $m_t = α_0\cdot x_t + z_t$, where $α_0\in \mathbb{R}^d$ is unknown to the learner and $z_t$ is randomly sampled from a noise distribution $\mathcal{F}$ with log-concave density function $f$. We consider both \emph{binary feedback} (the learner can only observe whether she wins or not) and \emph{full information feedback} (the learner can observe $m_t$) at the end of each time $t$. For binary feedback, when the noise distribution $\mathcal{F}$ is known, we propose a bidding algorithm, by using maximum likelihood estimation (MLE) method to achieve at most $\widetilde{O}(\sqrt{\log(d) T})$ regret. Moreover, we generalize this algorithm to the setting with binary feedback and the noise distribution is unknown but belongs to a parametrized family of distributions. For the full information feedback with \emph{unknown} noise distribution, we provide an algorithm that achieves regret at most $\widetilde{O}(\sqrt{dT})$. Our approach combines an estimator for log-concave density functions and then MLE method to learn the noise distribution $\mathcal{F}$ and linear weight $α_0$ simultaneously. We also provide a lower bound result such that any bidding policy in a broad class must achieve regret at least $Ω(\sqrt{T})$, even when the learner receives the full information feedback and $\mathcal{F}$ is known.
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。