报告题目：Making AI trustworthy: A statistical perspective

报告时间：2024年6月27日  14:30-15:30

报告地点：综合楼644

报告人：Qiang Sun

报告人简介：

Qiang Sun is currently an Associate Professor at the University of Toronto (UofT) and a visiting faculty at MBZUAI, leading the StatsLE (Statistics, Learning, and Engineering) Lab. Qiang is broadly interested in statistics + AI, with a focus on leveraging statistics to make AI reliable and trustworthy and efficient generative AI. Motivated by challenges in the industrial sector, his  interests extend to ensemble learning, and reinforcement learning.  He is also interested in AI for tech, finance, and science. Prior to his tenure at Uof , he wasan associate research scholar at Princeton University. He obtained his PhD from the University of North Carolina at Chapel Hill (UNC-CH) and his BS in SCGY from the University of Science and Technology of China (USTC). In addition to his faculty role, he also serves as an associate editor for Electronic Journal of Statistics (EJS) and as an area chair for various ML conferences.  

报告摘要：

Decision-making in high-stakes applications, such as healthcare and algorithmic trading, is increasingly data-driven and supported by deep learning models. However, these models are often fragile to slight environmental changes. How can we make them trustworthy? While explainability has been considered a path towards building trustworthy AI models, we argue that it is neither sufficient nor necessary. From a statistical perspective, we propose that algorithms must always generalize to the future consistently despite potential environmental shifts. In other words, a trustworthy algorithm should perform well across different conditions. We will discuss some of our recent studies and conclude with key take-away messages.