[Sds-seminars] [Sds-announce] S&DS Talk by Geoff Pleiss, 2/9. 4pm, "Bridging the Gap Between Deep Learning and Probabilistic Modeling"

[elizavette.torres at yale.edu]

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


GEOFF PLEISS, Columbia University


Wednesday, February 09, 2022

4:00PM to 5:00PM

Zoom: https://yale.zoom.us/j/93952040462

 <https://geoffpleiss.com/> Website

 

 

 

Title: Bridging the Gap Between Deep Learning and Probabilistic Modeling

Information and Abstract: 

Deep learning excels with large-scale unstructured data - common across many
modern application domains - while probabilistic modeling offers the ability
to encode prior knowledge and quantify uncertainty - necessary for
safety-critical applications and downstream decision-making tasks. I will
discuss examples from my research that bridge the gap between these two
learning paradigms. The first half will show that insights from deep
learning can improve the practicality of probabilistic models. I will
discuss work that scales Gaussian process regression, a common probabilistic
model, to datasets two orders of magnitude larger than previously reported.
The second half will show that probabilistic methods can improve our
understanding of deep learning. I will demonstrate that Gaussian process
theory uncovers new insights about the effects of width and depth in neural
networks. I will conclude with ongoing efforts to quantify neural network
uncertainty, develop new inductive biases, and other work at the
intersection of deep learning and probabilistic modeling.

Bio: Geoff Pleiss is a postdoctoral researcher at Columbia University,
hosted by John Cunningham, with affiliations in the Department of Statistics
and the Zuckerman Institute. He obtained his Ph.D. in Computer Science from
Cornell University, advised by Kilian Weinberger, and his B.Sc. from Olin
College of Engineering. His research interests are broadly situated in
machine learning, including neural networks, Gaussian processes, uncertainty
quantification, and scalability. Geoff is also the co-founder and maintainer
of the GPyTorch software framework.

 

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20220207/01714c91/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.jpg
Type: image/jpeg
Size: 2925 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20220207/01714c91/attachment.jpg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image002.jpg
Type: image/jpeg
Size: 39026 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20220207/01714c91/attachment-0001.jpg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image003.jpg
Type: image/jpeg
Size: 8035 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20220207/01714c91/attachment-0002.jpg>
-------------- next part --------------
-- 
Sds-announce mailing list
Sds-announce at mailman.yale.edu
https://mailman.yale.edu/mailman/listinfo/sds-announce