[Sds-seminars] Fwd: [Statseminars] S&DS Talk, Andrej Risteski, 2/25, "Better understanding of modern paradigms in probabilistic models" DL220

[Dan Spielman]

---------- Forwarded message ---------
From: Elizavette Torres <elizavette.torres at yale.edu>
Date: Fri, Feb 22, 2019 at 9:42 AM
Subject: [Statseminars] S&DS Talk, Andrej Risteski, 2/25, "Better
understanding of modern paradigms in probabilistic models" DL220
To: <Statseminars at mailman.yale.edu>, <sds-majors at mailman.yale.edu>


[image: Department of Statistics and Data Science]
<https://statistics.yale.edu/>*Department of Statistics and Data Science *
<https://statistics.yale.edu/>
ANDREJ RISTESKI, MIT



[image:
https://statistics.yale.edu/sites/default/files/styles/user_picture_node/public/photo_math.png?itok=PQooLet-]Date:
Monday, February 25, 2019

Time: 4:00PM to 5:15PM

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


10 Hillhouse Avenue, Room 220

New Haven, CT

Website <https://math.mit.edu/~risteski/>









*Better understanding of modern paradigms in probabilistic models*



*Information and Abstract: *

In recent years, one of the areas of machine learning that has seen the
most exciting progress is unsupervised learning, namely learning in the
absence of labels or annotation. An integral part of these advances have
been complex probabilistic models for high-dimensional data, capturing
different types of intricate latent structure. As a consequence, a lot of
statistical and algorithmic issues have emerged, stemming both
from learning (fitting a model from raw data) and inference (probabilistic
queries and sampling from a known model). A common theme is that the models
that are used in practice are often intractable in the worst-case
(computationally or statistically), yet even simple algorithms are, to
borrow from Wigner, unreasonably effective in practice. It thus behooves us
to ask why this happens.

I will showcase some of my research addressing this question, in the
context of computationally efficient inference using Langevin dynamics in
the presence of multimodality, as well as statistical guarantees for
learning distributions using GANs (Generative Adversarial Networks).

BIO: Andrej Risteski holds a joint position as the Norbert Wiener fellow at
the Institute for Data Science and Statistics (IDSS) and an Instructor of
Applied Mathematics at MIT.

Before coming to MIT, he was a PhD student in the Computer Science
Department at Princeton University, working under the advisement of Sanjeev
Arora. Prior to that he received his B.S.E. degree at Princeton University
as well.

His work lies in the intersection of machine learning and theoretical
computer science. The broad goal of his research is
theoretically understanding statistical and algorithmic phenomena and
problems arising in modern machine learning.



*3:45 p.m.**   Pre-talk tea Dunham Lab, Suite 222, Breakroom 228*

For more details and upcoming events visit our website at
http://statistics.yale.edu/ .






_______________________________________________
Statseminars mailing list
Statseminars at mailman.yale.edu
https://mailman.yale.edu/mailman/listinfo/statseminars
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20190222/332be7e2/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/20190222/332be7e2/attachment.jpg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image003.jpg
Type: image/jpeg
Size: 5963 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20190222/332be7e2/attachment-0001.jpg>
-------------- next part --------------
A non-text attachment was scrubbed...
Name: image002.jpg
Type: image/jpeg
Size: 46839 bytes
Desc: not available
URL: <http://mailman.yale.edu/pipermail/sds-seminars/attachments/20190222/332be7e2/attachment-0002.jpg>