Bo Waggoner, University of Colorado

Abstract

Loss functions are extremely useful in supervised machine learning to objectively evaluate, compare, and train models. On the other hand, it is not clear how to utilize loss functions for generative models such as GANs and Large Language Models, which use different learning paradigms and present unique challenges for evaluation. This talk will discuss these motivations and challenges and present results from a recent ICML paper, where we define and design loss functions for discrete black-box generative models. Based on joint work with Dhamma Kimpara and Rafael Frongillo, accessible at https://arxiv.org/abs/2211.03761.

[Video]

Speaker bio: Bo Waggoner is Assistant Professor of Computer Science at the University of Colorado, Boulder, where he is a member of the algorithmic economics, theoretical machine learning, and theoretical computer science groups. His research focuses on elicitation and aggregation of information for forecasting and decisionmaking. He received his PhD in Computer Science from Harvard in 2016 and completed postdocs at the University of Pennsylvania and Microsoft Research.