学 术 报 告
报告题目:面向隐私保护和通信有效的联邦多臂赌博机研究
Privacy-Preserving Communication-Efficient Federated Multi-Armed Bandits
报 告 人: 宋林琦 (香港城市大学)
报告时间: 2022年9月23日(周五)上午10:00
报告形式: 腾讯会议
会议 ID: 617 513 068
主办单位: bat365中文官方网站
Abstract: Communication bottleneck and data privacy are two critical concerns in federated multi-armed bandit (MAB) problems, such as situations in decision-making and recommendations of connected vehicles via wireless. In this talk, we will talk about how to design the privacy-preserving communication-efficient algorithm in such problems and study the interactions among privacy, communication, and learning performance in terms of the regret. Furthermore, we adopt the differential privacy (DP) approach to protect the data privacy at each agent when exchanging information; and we curtail communication costs by making less frequent communications with fewer agents participation. By analyzing the regret of our proposed algorithmic framework in both master-worker and decentralized network structures, we theoretically show trade-offs between regret and communication costs/privacy, namely, less communication costs and higher privacy requirements lead to more regret in the federated MAB problem.
报告人简介:
宋林琦博士,现为香港城市大学计算机科学系助理教授、香港城市大学深圳研究院副研究员。获得清华大学本科、硕士学位,及加州大学洛杉矶分校(UCLA)博士学位。研究方向包括信息论、联邦学习和自然语言处理。宋林琦博士在信息理论领域主流学术刊物IEEE TIT及IEEE JSAC、ACL、EMNLP等发表论文80余篇。获得香港研究资助局的Early Career Scheme及IEEE MIPR 2020的最佳论文奖。宋林琦博士担任Intelligent and Converged Networks的副主编、Journal of Franklin Institute和Digital Signal Processing等杂志的客座编委。主持或联合主持多项科研项目,包括香港政府研究资助局项目、香港政府创新及科技基金项目、广东省基础与应用基础研究基金重点项目、广东省国际合作项目、深圳市技术攻关项目、湖南长沙国际合作项目、腾讯校企合作项目等。
bat365中文官方网站
2022年9月19日