讲座信息
主题:机器学习中的数据定价
What is your data worth? Quantifying data value in machine learning
嘉宾:贾若溪 Ruoxi Jia
地点:腾讯会议
时间:2022/3/27(周日)20:00
关注统计之都公众号,后台发送“云讲堂”即可获取会议ID
活动志愿者(如会议记录、资料整理)报名,请在后台发送“志愿者
讲座摘要
People share massive amounts of their personal data with companies every day and these data are used to generate tremendous business values. Some economists, politicians, and activists argue that people should be paid for their contributions—but the million-dollar question is: by how much? This question becomes even more difficult to answer in the era of machine learning: data is used to train models and the value of data largely depends on how good the models are. In this talk, I will present some recent work on data valuation for machine learning. I will start by introducing a principled notion for data value and then present a suite of algorithms that we developed to efficiently compute the data value. I will then discuss how to adapt this notion to value data in federated learning settings. At last, I will discuss the implications of data valuation to enhancing interpretability, robustness, security, and efficiency of machine learning systems.
个人简介
Ruoxi Jia joined Virginia Tech in 2020 as an assistant professor in the the Bradley Department of Electrical and Computer Engineering at Virginia Tech. She earned her PhD in the EECS Department from UC Berkeley in 2018 and a B.S. from Peking University in 2013. Jia's research interest lies broadly in the span of machine learning, security, privacy, and cyber-physical systems. Jia's recent work focuses on building algorithmic foundations for data markets and developing trustworthy machine learning methods. Ruoxi is the recipient of the Chiang Fellowship for Graduate Scholars in Manufacturing and Engineering, the 8108 Alumni Fellowship, and the Okamatsu Fellowship, Virginia’s Commonwealth Cyber Initiative Award, and the Cisco Research Award. She was selected for the Rising Stars in the EECS program in 2017. Ruoxi’s work has been featured in multiple media outlets.
统计之都(Capital of Statistics,简称 COS)成立于 2006 年,是一个旨在推广与应用统计学、数据科学知识的公益性网站和社区。
统计之都以专业、人本、正直、团结的理念尝试推动统计和数据科学在中国的发展,促进各行业的创新和繁荣。
统计之都的数据科学云讲座是由统计之都发起,由全球志愿者共同组织的开放性公益活动。
如果您愿意奉献自己的力量(组织、宣传、编辑、翻译、剪辑等),欢迎关注微信公众号后发送"志愿者"、"云讲座"按指引进一步沟通!
继续阅读
阅读原文