[Sds-seminars] S&DS Seminar, Jason Altschuler, 9/26, 4pm-5pm, DL220, "Privacy of Noisy SGD"

[elizavette.torres at yale.edu]

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

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

Jason Altschuler, NYU

In-Person

Monday, September 26, 2022

4:00PM to 5:00PM

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

10 Hillhouse Avenue

New Haven, CT 06511

 <https://www.mit.edu/~jasonalt/> Website



Zoom Link:

https://yale.zoom.us/j/92411077917?pwd=aXhnTnFGRXFoaTVDczNjeFFKeWpTQT09

Password: 24



Title: Privacy of Noisy SGD



Information and Abstract:

A central issue in machine learning is how to train models on sensitive user
data. Industry has widely adopted a simple algorithm: Stochastic Gradient
Descent with noise (aka Stochastic Gradient Langevin Dynamics). However,
foundational questions about this algorithm’s privacy loss remain open-even
in the seemingly simple setting of smooth convex losses over a bounded
domain. Our main result resolves these questions by characterizing the
differential privacy up to a constant factor. This result reveals that all
previous analyses for this setting have the wrong qualitative behavior.
Specifically, while previous privacy analyses increase ad infinitum in the
number of iterations, we show that after a small burn-in period, running SGD
longer leaks no further privacy.

In this talk, I will describe this result and our analysis-which departs
from previous approaches based on fast mixing, instead using techniques
based on optimal transport.

Joint work with Kunal Talwar

 <x-apple-data-detectors://10/> 3:30pm -   Pre-talk meet and greet.



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/20220926/b679eb61/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/20220926/b679eb61/attachment.jpg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image002.jpg
Type: image/jpeg
Size: 67985 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20220926/b679eb61/attachment-0001.jpg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image003.jpg
Type: image/jpeg
Size: 7403 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20220926/b679eb61/attachment-0002.jpg>