[Sds-seminars] [Sds-announce] Fwd: [YINS] 10/6 YINS Seminar Series: Daniel Hsu (Columbia)

Dan Spielman daniel.spielman at yale.edu
Mon Oct 4 13:43:41 EDT 2021


---------- Forwarded message ---------
From: Hau, Emily <emily.hau at yale.edu>
Date: Mon, Oct 4, 2021 at 12:14 PM
Subject: [YINS] 10/6 YINS Seminar Series: Daniel Hsu (Columbia)
To: yins at mailman.yale.edu <yins at mailman.yale.edu>


[image: cid:image001.png at 01D7A63A.45D30410]



*YINS Seminar Series: Wednesday, October 6, 2021 at 12:00pm*
“Contrastive learning, multi-view redundancy, and linear models”
*Speaker: Daniel Hsu **Associate Professor, Columbia University*  Abstract:
Contrastive learning is a “self-supervised” approach to representation
learning that uses naturally occurring similar and dissimilar pairs of data
points to find useful embeddings of data. We study contrastive learning in
the context of multi-view statistical models. First, we show that whenever
the views of the data are approximately redundant in their ability to
predict a target function, a low-dimensional embedding obtained via
contrastive learning affords a linear predictor with near-optimal
predictive accuracy. Second, we show that in the context of topic models,
the embedding can be interpreted as a linear transformation of the
posterior moments of the hidden topic distribution given the observed
words. We also empirically demonstrate that linear classifiers with these
representations perform well in document classification tasks with very few
labeled examples in a semi-supervised setting.    This is joint work with
Akshay Krishnamurthy (MSR) and Christopher Tosh (Columbia).    Speaker
Bio: Daniel
Hsu is an associate professor in the Department of Computer Science and a
member of the Data Science Institute, both at Columbia University.
Previously, he was a postdoc at Microsoft Research New England, and the
Departments of Statistics at Rutgers University and the University of
Pennsylvania. He holds a Ph.D. in Computer Science from UC San Diego, and a
B.S. in Computer Science and Engineering from UC Berkeley. He was selected
by IEEE Intelligent Systems as one of “AI’s 10 to Watch” in 2015 and
received a 2016 Sloan Research Fellowship. Daniel’s research interests are
in algorithmic statistics and machine learning. To participate:
Join from PC, Mac, Linux, iOS or Android: https://yale.zoom.us/j/93949928143
      Or Telephone:203-432-9666 (2-ZOOM if on-campus) or 646 568 7788
      Meeting ID: 939 4992 8143
      International numbers available: https://yale.zoom.us/u/af5ZYLPKB



*Upcoming YINS Seminars:*



10/13/21 Steve Hanneke (Purdue)
<https://yins.yale.edu/event/yins-seminar-steve-hanneke-purdue>

10/20/21 Avrim Blum (TTIC)
<https://yins.yale.edu/event/yins-seminar-avrim-blum-ttic>

10/27/21 Yasaman Bahri (Google Brain)
<https://yins.yale.edu/event/yins-industry-seminar-yasaman-bahri-google>

11/3/21 Marinka Zitnik (Harvard)
<https://yins.yale.edu/event/yins-seminar-marinka-zitnik-harvard>



Click here to subscribe to YINS emails.
<https://mailman.yale.edu/mailman/listinfo/yins>





Emily E. H. Hau | Director, Programs and Partnerships

*Yale Institute for Network Science*

*Yale University*

*17 Hillhouse Avenue | Room 341 | New Haven, CT 06511*

c: (203) 273-7886

*emily.hau at yale.edu <emily.hau at yale.edu>*


_______________________________________________
YINS mailing list
YINS at mailman.yale.edu
https://mailman.yale.edu/mailman/listinfo/yins
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20211004/14655f69/attachment.html>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image001.png
Type: image/png
Size: 89590 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20211004/14655f69/attachment.png>
-------------- next part --------------
-- 
Sds-announce mailing list
Sds-announce at mailman.yale.edu
https://mailman.yale.edu/mailman/listinfo/sds-announce


More information about the Sds-seminars mailing list