Details
"Uncertainty quantification of the generative models and by the generative models”
Abstract: In this talk, I will discuss some recent progress on quantifying the epistemic uncertainty of large language models (LLMs). I will draw inspiration from existing works that quantifies uncertainty in forecasting problems and apply the intuition to the generative models. I will then discuss new Bayesian uncertainty quantification algorithms arising from the reverse diffusion processes. Advances in these algorithms also help reduce the intermediary steps in the diffusion models.
Yian Ma is an assistant professor at the Halıcıoğlu Data Science Institute, UC San Diego, where he serves as the vice chair in charge of the graduate programs. Prior to UCSD, he spent a year as a visiting faculty at Google Research. Before that, he was a post-doctoral fellow at UC Berkeley, hosted by Mike Jordan. Yian completed his Ph.D. at University of Washington. His current research primarily revolves around scalable inference methods for credible machine learning, with application to time series data and sequential decision making tasks. He has received the Facebook research award, the Stein fellowship, and the best paper awards at the Neurips and ICML workshops.
Light refreshments will be available