[Sds-seminars] S&DS In-Person Seminar, Joan Bruna, 12/12, 4pm-5pm, "On Symmetries and Feature Learning in Simple Neural Networks"

[elizavette.torres at yale.edu]

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

In-Person seminars will be held at Dunham Lab, 10 Hillhouse Ave., Room 220,
with an option of remote participation via zoom.

 <x-apple-data-detectors://10/> 3:30pm -   Pre-talk meet and greet, DL Suite
222, Room 228



 <https://statistics.yale.edu/seminars/joan-bruna-1> Joan Bruna, New York
University



Date: Monday, December 12, 2022

Time: 4:00PM to 5:00PM

Location: Dunbar Lab.  <http://maps.google.com/?q=10+Hillhouse+Avenue%2C+Rm.
+220%2C+New+Haven%2C+CT%2C+06511%2C+us> see map

10 Hillhouse Avenue, Rm. 220

New Haven, CT 06511

https://statistics.yale.edu/seminars/joan-bruna-1



Zoom Option:
https://yale.zoom.us/j/92411077917?pwd=aXhnTnFGRXFoaTVDczNjeFFKeWpTQT09  /
Password: 24



Title: On Symmetries and Feature Learning in Simple Neural Networks



Information and Abstract:

For all their mathematical mysteries, two important features of neural
networks are their ability to encode symmetries into their architectures,
and their ability to ‘discover’ hidden low-dimensional structures within
high-dimensional data.  In this talk, I will cover two snippets capturing
each of these phenomena. In the first part, we will study approximation
properties of symmetric and antisymmetric functions by neural networks, and
establish an exponential advantage of pairwise models (underpinning
transformers) over unary ones (underpinning ‘DeepSets’). In the second
part, we study the learnability of ‘single-index models’, a class of
semiparametric models with hidden low-dimensional structure, and show how
shallow neural networks are able to learn them with near optimal sample
complexity, showcasing the benefits of feature learning in the
high-dimensional regime.

Joint work with A. Zweig (first part) and A. Bietti, MJ Song and C. Sanford
(second part).

In-Person seminars will be held at Dunham Lab, 10 Hillhouse Ave., Room 220,
with an option of remote participation via zoom.

Link: Join from PC, Mac, Linux, iOS or Android:
https://yale.zoom.us/j/92411077917?pwd=aXhnTnFGRXFoaTVDczNjeFFKeWpTQT09

Password: 24

Or Telephone：203-432-9666 (2-ZOOM if on-campus) or 646 568 7788

Meeting ID: 924 1107 7917










Department of Statistics and Data Science


Yale University
24 Hillhouse Avenue
New Haven, CT 06511

t 203.432.0666
f 203.432.0633





-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20221207/c85c3976/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/20221207/c85c3976/attachment.jpg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image002.jpg
Type: image/jpeg
Size: 31709 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20221207/c85c3976/attachment-0001.jpg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image004.jpg
Type: image/jpeg
Size: 3674 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20221207/c85c3976/attachment-0002.jpg>