国产精品无码午夜福利 ,精品久久久久久亚洲中文字幕,韩国av片永久免费

題目：Information Design under Privacy Constraints

時(shí)間：2024年10月29日14:00-15:30

地點(diǎn)：教二2114

匯報(bào)人：鄭舒冉（清華大學(xué)交叉信息研究院助理教授）

主持人：鄺仲弘（中國人民大學(xué)經(jīng)濟(jì)學(xué)院副教授）

摘要：The talk will be focusing on information design under privacy constraints. Information disclosure can compromise privacy when revealed information is correlated with private information. In this first part of the talk, we consider the notion of inferential privacy, which measures privacy leakage by bounding the inferential power a Bayesian adversary can gain by observing a released signal. Our goal is to devise an inferentially-private private information structure that maximizes the informativeness of the released signal, following the Blackwell ordering principle, while adhering to inferential privacy constraints. In this second part of the talk, we study Bayesian persuasion under differential privacy constraints, where the sender must design an optimal signaling scheme for persuasion while guaranteeing the privacy of each agent's private information in the database. To understand how privacy constraints affect information disclosure, we explore two perspectives within Bayesian persuasion: one views the mechanism as releasing a posterior about the private data, while the other views it as sending an action recommendation.

個(gè)人簡介：鄭舒冉是清華大學(xué)交叉信息研究院助理教授。她在2022年于哈佛大學(xué)取得計(jì)算機(jī)科學(xué)博士學(xué)位，后在2023年于卡內(nèi)基梅隆大學(xué)擔(dān)任博士后研究員。在2022年秋，鄭舒冉于谷歌紐約研究院擔(dān)任博士生研究員。她的主要研究方向?yàn)橛?jì)算經(jīng)濟(jì)學(xué)，研究目標(biāo)是利用經(jīng)濟(jì)學(xué)工具理解數(shù)據(jù)和信息在計(jì)算機(jī)科學(xué)問題中的價(jià)值。