Generative Modeling by Estimating Gradients of the Data Distribution - Stefano Ermon

Seminar on Theoretical Machine Learning
Topic: Generative Modeling by Estimating Gradients of the Data Distribution
Speaker: Stefano Ermon
Affiliation: Stanford University
Date: May 12, 2020
For more video please visit video.ias.edu

[@edvinbeqari7551]

How is the dlog_p(x) used in the cost function and reverse diffusion at the same time?

[@homataha5626]

is the slide available?

[@fredxu9826]

instead of using Lagevin, is it possible to do HMC for score-based sampling? If so are the pitfalls avoided?

[@X.A.N.A..]

WOOOOOOOOOOOOOOOOOOOOOOOOOOOOO

[@X.A.N.A..]

Who disliked this?

[@X.A.N.A..]

Langevin dynamics? More like Langewin Dynamics