On Mon September 19, 2022

Speaker

Kangwook Lee


Title

Recent Advances in Trustworthy Machine Learning


Abstract

In this talk, I will discuss recent advances in trustworthy machine learning. In the first part, I will explain why current machine learning algorithms and systems are not trustworthy -- they are neither fair, robust, private, nor ethical. This calls for the need for a novel approach to design trustworthy machine learning algorithms and systems. I will then share two drastically different approaches to tackle this challenge -- multi-level programming and language models.


Bio

Kangwook Lee is an Assistant Professor at the Electrical and Computer Engineering department and the Computer Sciences department (by courtesy) at the University of Wisconsin-Madison. He is also leading deep learning research at Krafton. Previously, he was a Research Assistant Professor at the Information and Electronics Research Institute of KAIST and was a postdoctoral scholar at the same institute. He received his PhD in 2016 from the Electrical Engineering and Computer Science department at UC Berkeley. He is the recipient of The IEEE Joint Communications Society/Information Theory Society Paper Award (2020) and the KSEA Young Investigator Grants Award (2022).


Language

English