• Upcoming Events
  • Awards
  • Distinguished Lecture
  • Latest Seminars and Events
  • Others
  • Seminars
  • Workshop and Conference
  • Past Events
  • Student Issue
Upcoming Events
Topic:Provable Learning from Data with Priors: from Low-rank to Diffusion Models
Date:04/01/2024
Time:2:30 pm - 3:30 pm
Venue:Lady Shaw Building LT2
Category:Latest Seminars and Events
Speaker:Professor Yuejie Chi
PDF:Prof.-Yuejie-Chi_4-JAN.pdf
Details:

Abstract

Generative priors are effective tools to combat the curse of dimensionality, and enable efficient learning that otherwise will be ill-posed, in data science. This talk starts with the classical low-rank prior, by discussing how the trick of preconditioning boosts the learning speed of gradient descent without compensating generalization in overparameterized low-rank models, unveiling the phenomenon of implicit regularization. The talk next discusses non-asymptotic theory towards understanding the data generation process of diffusion models in discrete time, assuming access to reasonable estimates of the score functions.