|Provable Learning from Data with Priors: from Low-rank to Diffusion Models
|2:30 pm - 3:30 pm
|Lady Shaw Building LT2
|Latest Seminars and Events
|Professor Yuejie Chi
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.