Proceedings of the 23rd ACM Conference on Economics and Computation最新文献_第10页

Online Bayesian Recommendation with No Regret 无悔的在线贝叶斯推荐

Proceedings of the 23rd ACM Conference on Economics and Computation Pub Date : 2022-02-12 DOI: 10.1145/3490486.3538327

Yiding Feng, Wei Tang, Haifeng Xu

{"title":"Online Bayesian Recommendation with No Regret","authors":"Yiding Feng, Wei Tang, Haifeng Xu","doi":"10.1145/3490486.3538327","DOIUrl":"https://doi.org/10.1145/3490486.3538327","url":null,"abstract":"We introduce and study the online Bayesian recommendation problem for a platform, who can observe a utility-relevant state of a product, repeatedly interacting with a population of myopic users through an online recommendation mechanism. This paradigm is common in a wide range of scenarios in the current Internet economy. For each user with her own private preference and belief, the platform commits to a recommendation strategy to utilize his information advantage on the product state to persuade the self-interested user to follow the recommendation. The platform does not know user's preferences and beliefs, and has to use an adaptive recommendation strategy to persuade with gradually learning user's preferences and beliefs in the process. We aim to design online learning policies with no Stackelberg regret for the platform, i.e., against the optimum policy in hindsight under the assumption that users will correspondingly adapt their behaviors to the benchmark policy. Our first result is an online policy that achieves double logarithm regret dependence on the number of rounds. We then present a hardness result showing that no adaptive online policy can achieve regret with better dependency on the number of rounds. Finally, by formulating the platform's problem as optimizing a linear program with membership oracle access, we present our second online policy that achieves regret with polynomial dependence on the number of states but logarithm dependence on the number of rounds.","PeriodicalId":209859,"journal":{"name":"Proceedings of the 23rd ACM Conference on Economics and Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133503566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Faster No-Regret Learning Dynamics for Extensive-Form Correlated and Coarse Correlated Equilibria 广义相关均衡与粗相关均衡的快速无遗憾学习动力学

Proceedings of the 23rd ACM Conference on Economics and Computation Pub Date : 2022-02-11 DOI: 10.1145/3490486.3538288

Ioannis Anagnostides, Gabriele Farina, Christian Kroer, A. Celli, T. Sandholm

{"title":"Faster No-Regret Learning Dynamics for Extensive-Form Correlated and Coarse Correlated Equilibria","authors":"Ioannis Anagnostides, Gabriele Farina, Christian Kroer, A. Celli, T. Sandholm","doi":"10.1145/3490486.3538288","DOIUrl":"https://doi.org/10.1145/3490486.3538288","url":null,"abstract":"A recent emerging trend in the literature on learning in games has been concerned with providing faster learning dynamics for correlated and coarse correlated equilibria in normal-form games. Much less is known about the significantly more challenging setting of extensive-form games, which can capture both sequential and simultaneous moves, as well as imperfect information. In this paper we establish faster no-regret learning dynamics forextensive-form correlated equilibria (EFCE) in multiplayer general-sum imperfect-information extensive-form games. When all players follow our accelerated dynamics, the correlated distribution of play is an O(T-3/4)-approximate EFCE, where the O(·) notation suppresses parameters polynomial in the description of the game. This significantly improves over the best prior rate of O(T-1/2 ). To achieve this, we develop a framework for performing accelerated Phi-regret minimization via predictions. One of our key technical contributions---that enables us to employ our generic template---is to characterize the stability of fixed points associated with trigger deviation functions through a refined perturbation analysis of a structured Markov chain. Furthermore, for the simpler solution concept of extensive-form coarse correlated equilibrium (EFCCE) we give a new succinct closed-form characterization of the associated fixed points, bypassing the expensive computation of stationary distributions required for EFCE. Our results place EFCCE closer to normal-form coarse correlated equilibria in terms of the per-iteration complexity, although the former prescribes a much more compelling notion of correlation. Finally, experiments conducted on standard benchmarks corroborate our theoretical findings.","PeriodicalId":209859,"journal":{"name":"Proceedings of the 23rd ACM Conference on Economics and Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124828515","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 6

Improved Upper Bounds for Finding Tarski Fixed Points 改进了寻找Tarski不动点的上界

Proceedings of the 23rd ACM Conference on Economics and Computation Pub Date : 2022-02-11 DOI: 10.1145/3490486.3538297

X. Chen, Yuhao Li

引用次数: 2

Closure Operators: Complexity and Applications to Classification and Decision-making 闭包操作符:复杂性及其在分类和决策中的应用

Proceedings of the 23rd ACM Conference on Economics and Computation Pub Date : 2022-02-10 DOI: 10.1145/3490486.3538253

Hamed Hamze Bajgiran, F. Echenique

引用次数: 0

Sequential Veto Bargaining with Incomplete Information 不完全信息下的顺序否决权议价

Proceedings of the 23rd ACM Conference on Economics and Computation Pub Date : 2022-02-05 DOI: 10.1145/3490486.3538362

S. N. Ali, Navin Kartik, Andreas Kleiner

引用次数: 2

A Population's Feasible Posterior Beliefs 人口的可行后验信念

Proceedings of the 23rd ACM Conference on Economics and Computation Pub Date : 2022-02-03 DOI: 10.1145/3490486.3538234

Itai Arieli, Y. Babichenko

引用次数: 6

Long-term Data Sharing under Exclusivity Attacks 排他性攻击下的长期数据共享

Proceedings of the 23rd ACM Conference on Economics and Computation Pub Date : 2022-01-22 DOI: 10.1145/3490486.3538311

Yotam gafni, Moshe Tennenholtz

引用次数: 0

Optimal and Differentially Private Data Acquisition: Central and Local Mechanisms 最优和差异化私有数据获取:中央和局部机制

Proceedings of the 23rd ACM Conference on Economics and Computation Pub Date : 2022-01-10 DOI: 10.1145/3490486.3538329

Alireza Fallah, A. Makhdoumi, Azarakhsh Malekian, A. Ozdaglar

{"title":"Optimal and Differentially Private Data Acquisition: Central and Local Mechanisms","authors":"Alireza Fallah, A. Makhdoumi, Azarakhsh Malekian, A. Ozdaglar","doi":"10.1145/3490486.3538329","DOIUrl":"https://doi.org/10.1145/3490486.3538329","url":null,"abstract":"We consider a platform's problem of collecting data from privacy sensitive users to estimate an underlying parameter of interest. We formulate this question as a Bayesian-optimal mechanism design problem, in which an individual can share her (verifiable) data in exchange for a monetary reward or services, but at the same time has a (private) heterogeneous privacy cost which we quantify using differential privacy. We consider two popular differential privacy settings for providing privacy guarantees for the users: central and local. In both settings, we establish minimax lower bounds for the estimation error and derive (near) optimal estimators for given heterogeneous privacy loss levels for users. Building on this characterization, we pose the mechanism design problem as the optimal selection of an estimator and payments that will elicit truthful reporting of users' privacy sensitivities. Under a regularity condition on the distribution of privacy sensitivities we develop efficient algorithmic mechanisms to solve this problem in both privacy settings. Our mechanism in the central setting can be implemented in time O (n log n) where n is the number of users and our mechanism in the local setting admits a Polynomial Time Approximation Scheme (PTAS). The full paper is available at: https://arxiv.org/abs/2201.03968","PeriodicalId":209859,"journal":{"name":"Proceedings of the 23rd ACM Conference on Economics and Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-01-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115957811","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 13

Auction Throttling and Causal Inference of Online Advertising Effects 拍卖节流与网络广告效应的因果推理

Proceedings of the 23rd ACM Conference on Economics and Computation Pub Date : 2021-12-30 DOI: 10.1145/3490486.3538246

George Gui, Harikesh S. Nair, Fengshi Niu

{"title":"Auction Throttling and Causal Inference of Online Advertising Effects","authors":"George Gui, Harikesh S. Nair, Fengshi Niu","doi":"10.1145/3490486.3538246","DOIUrl":"https://doi.org/10.1145/3490486.3538246","url":null,"abstract":"Causally identifying the effect of digital advertising is challenging, because experimentation is expensive, and observational data lacks random variation. This paper identifies a pervasive source of naturally occurring, quasi-experimental variation in user-level ad-exposure in digital advertising campaigns. It shows how this variation can be utilized by ad-publishers to identify the causal effect of advertising campaigns. The variation pertains to auction throttling, a probabilistic method of budget pacing that is widely used to spread an ad-campaign's budget over its deployed duration, so that the campaign's budget is not exceeded or overly concentrated in any one period. The throttling mechanism is implemented by computing a participation probability based on the campaign's budget spending rate and then including the campaign in a random subset of available ad-auctions each period according to this probability. We show that access to logged-participation probabilities enables identifying the local average treatment effect (LATE) in the ad-campaign. We present a new estimator that leverages this identification strategy and outline a bootstrap procedure for quantifying its variability. We apply our method to real-world ad-campaign data from an e-commerce advertising platform, which uses such throttling for budget pacing. We show our estimate is statistically different from estimates derived using other standard observational methods such as OLS and two-stage least squares estimators. Our estimated conversion lift is 110%, a more plausible number than 600%, the conversion lifts estimated using naive observational methods. The full version of the paper : https://arxiv.org/abs/2112.15155","PeriodicalId":209859,"journal":{"name":"Proceedings of the 23rd ACM Conference on Economics and Computation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2021-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129843298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 5

Private Private Information 私人信息

Proceedings of the 23rd ACM Conference on Economics and Computation Pub Date : 2021-12-29 DOI: 10.1145/3490486.3538348

Kevin He, Fedor Sandomirskiy, O. Tamuz

引用次数: 10