[Sds-seminars] [Sds-announce] S&DS Talk by Yang Song, 2/21, 4pm, "Learning to Generate Data by Estimating Gradients of the Data Distribution"

[elizavette.torres at yale.edu]

   <https://statistics.yale.edu/> Department of Statistics and Data Science  


YANG SONG, Stanford University


Monday, February 21, 2022

4:00PM to 5:00PM

Zoom: https://yale.zoom.us/j/92366427609

 <https://yang-song.github.io/> Website

 

 

Title: Learning to Generate Data by Estimating Gradients of the Data Distribution

 

Information and Abstract: 

 ​​Generating data with complex patterns, such as images, audio, and molecular structures, requires fitting very flexible statistical models to the data distribution. Even in the age of deep neural networks, building such models is difficult because they typically require an intractable normalization procedure to represent a probability distribution. To address this challenge, I propose to model the vector field of gradients of the data distribution (known as the score function), which does not require normalization and therefore can take full advantage of the flexibility of deep neural networks. I will show how to (1) estimate the score function from data with flexible deep neural networks and principled statistical methods, (2) generate new data using stochastic differential equations and Markov chain Monte Carlo, and even (3) evaluate probabilities as in a traditional statistical model. The resulting method, called score-based generative modeling, achieves record-breaking performance in applications including image synthesis, text-to-speech generation, time series prediction, and point cloud generation, challenging the long-time dominance of generative adversarial networks (GANs) on many of these tasks. Furthermore, unlike GANs, score-based generative models are suitable for Bayesian reasoning tasks such as solving ill-posed inverse problems, and I have demonstrated their superior performance on examples like sparse-view computed tomography and accelerated magnetic resonance imaging. Finally, I will discuss how score-based generative modeling opens up new opportunities and new future research directions for building better machines to create and understand complex data in various disciplines of science and engineering.

Bio: Yang Song is a final year Ph.D. student at Stanford University. His research interest is in deep generative models and their applications to inverse problem solving and AI safety. His first-author papers have been recognized with an Outstanding Paper Award at ICLR-2021, and an oral presentation at NeurIPS-2019. He is a recipient of the Apple PhD Fellowship in AI/ML, the J.P. Morgan PhD Fellowship, and the WAIC Rising Star Award.

 

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20220221/fc361163/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 6496 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20220221/fc361163/attachment.png>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image003.jpg
Type: image/jpeg
Size: 21571 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20220221/fc361163/attachment.jpg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image002.jpg
Type: image/jpeg
Size: 3107 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20220221/fc361163/attachment-0001.jpg>
-------------- next part --------------
-- 
Sds-announce mailing list
Sds-announce at mailman.yale.edu
https://mailman.yale.edu/mailman/listinfo/sds-announce