Provable Learning from Data with Priors: from Low-rank to Diffusion Models

Speaker:  Yuejie Chi – Pittsburgh, PA, United States
Topic(s):  Artificial Intelligence, Machine Learning, Computer Vision, Natural language processing , Computational Theory, Algorithms and Mathematics

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.

About this Lecture

Number of Slides:  40
Duration:  45 minutes
Languages Available:  English
Last Updated: 

Request this Lecture

To request this particular lecture, please complete this online form.

Request a Tour

To request a tour with this speaker, please complete this online form.

All requests will be sent to ACM headquarters for review.