关于全变差距离下机制设计的鲁棒性
On the Robustness of Mechanism Design under Total Variation Distance
AI总结:
研究在总变差距离下机制设计的鲁棒性,证明DSIC和BIC机制对接近先验的分布强鲁棒,并应用于收入最优、相关性鲁棒及先知不等式等场景。
摘要:
我们研究了当智能体的估值函数来自未知且相关的先验分布时,机制设计的问题。具体而言,给定一个先验分布 $\D$,我们感兴趣的是设计一个(诚实的)机制,使得该机制对于所有在总变差(TV)距离上接近 $\D$ 的“真实分布”都具有良好性能。我们证明了在此设置下,对于任何有界目标函数 $\Ocal$,DSIC 和 BIC 机制相对于 TV 距离是强鲁棒的,这扩展了 Brustle 等人(\cite{Brustle2020},EC 2020)最近的结果。我们结果的核心是总变差距离的一个基本对偶性质。作为我们结果的直接应用,我们(i)展示了如何为弱相关先验分布找到近似收入最优且近似 BIC 的机制;(ii)展示了当只能获得边际分布的“带噪声”版本时,如何找到相关性鲁棒机制,扩展了 Bei 等人(\cite{bei2019correlation},SODA 2019)最近的结果;(iii)证明了先知不等式类型的保证对于相关先验仍然成立,恢复了 D{ü}tting 和 Kesselheim(\cite{Dutting19},EC 2019)结果的一个变体;(iv)为相关分布见证简单机制与最优机制之间收入的无限分离给出了一个新的必要条件,补充了 Psomas 等人(\cite{psomas2022infinite},NeurIPS 2022)最近的结果;(v)对于单个智能体且其类型来自可由马尔可夫随机场捕获的相关分布的情况,给出了简单机制近似收入最优机制的一个新条件,补充了 Cai 和 Oikonomou(\cite{Cai21},EC 2021)最近的结果。
英文摘要:
We study the problem of designing mechanisms when agents' valuation functions are drawn from unknown and correlated prior distributions. In particular, we are given a prior distribution $\D$, and we are interested in designing a (truthful) mechanism that has good performance for all ``true distributions'' that are close to $\D$ in Total Variation (TV) distance. We show that DSIC and BIC mechanisms in this setting are strongly robust with respect to TV distance, for any bounded objective function $\Ocal$, extending a recent result of Brustle et al. (\cite{Brustle2020}, EC 2020). At the heart of our result is a fundamental duality property of total variation distance. As direct applications of our result, we (i) demonstrate how to find approximately revenue-optimal and approximately BIC mechanisms for weakly dependent prior distributions; (ii) show how to find correlation-robust mechanisms when only ``noisy'' versions of marginals are accessible, extending recent results of Bei et. al. (\cite{bei2019correlation}, SODA 2019); (iii) prove that prophet-inequality type guarantees are preserved for correlated priors, recovering a variant of a result of D{ü}tting and Kesselheim (\cite{Dutting19}, EC 2019); (iv) give a new necessary condition for a correlated distribution to witness an infinite separation in revenue between simple and optimal mechanisms, complementing recent results of Psomas et al. (\cite{psomas2022infinite}, NeurIPS 2022); (v) give a new condition for simple mechanisms to approximate revenue-optimal mechanisms for the case of a single agent whose type is drawn from a correlated distribution that can be captured by a Markov Random Field, complementing recent results of Cai and Oikonomou (\cite{Cai21}, EC 2021).
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。