<div dir="ltr">A gentle reminder that the talk will be tomorrow noon.</div><div class="gmail_extra"><br><div class="gmail_quote">On Sat, Jan 28, 2017 at 12:00 PM,  <span dir="ltr"><<a href="mailto:ai-seminar-announce-request@cs.cmu.edu" target="_blank">ai-seminar-announce-request@cs.cmu.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Send ai-seminar-announce mailing list submissions to<br>
        <a href="mailto:ai-seminar-announce@cs.cmu.edu">ai-seminar-announce@cs.cmu.edu</a><br>
<br>
To subscribe or unsubscribe via the World Wide Web, visit<br>
        <a href="https://mailman.srv.cs.cmu.edu/mailman/listinfo/ai-seminar-announce" rel="noreferrer" target="_blank">https://mailman.srv.cs.cmu.<wbr>edu/mailman/listinfo/ai-<wbr>seminar-announce</a><br>
or, via email, send a message with subject or body 'help' to<br>
        <a href="mailto:ai-seminar-announce-request@cs.cmu.edu">ai-seminar-announce-request@<wbr>cs.cmu.edu</a><br>
<br>
You can reach the person managing the list at<br>
        <a href="mailto:ai-seminar-announce-owner@cs.cmu.edu">ai-seminar-announce-owner@cs.<wbr>cmu.edu</a><br>
<br>
When replying, please edit your Subject line so it is more specific<br>
than "Re: Contents of ai-seminar-announce digest..."<br>
<br>
<br>
Today's Topics:<br>
<br>
   1.  AI Lunch -- Po-Wei Wang -- January 31 (Adams Wei Yu)<br>
<br>
<br>
------------------------------<wbr>------------------------------<wbr>----------<br>
<br>
Message: 1<br>
Date: Fri, 27 Jan 2017 13:43:20 -0500<br>
From: Adams Wei Yu <<a href="mailto:weiyu@cs.cmu.edu">weiyu@cs.cmu.edu</a>><br>
To: <a href="mailto:ai-seminar-announce@cs.cmu.edu">ai-seminar-announce@cs.cmu.edu</a><br>
Subject: [AI Seminar] AI Lunch -- Po-Wei Wang -- January 31<br>
Message-ID:<br>
        <<a href="mailto:CABzq7erCO_7iHYp0zr5EaNqt2sf7t%2BUkWPH6UEqWpOmaSO4RiQ@mail.gmail.com">CABzq7erCO_<wbr>7iHYp0zr5EaNqt2sf7t+<wbr>UkWPH6UEqWpOmaSO4RiQ@mail.<wbr>gmail.com</a>><br>
Content-Type: text/plain; charset="utf-8"<br>
<br>
Dear faculty and students,<br>
<br>
We look forward to seeing you Next Tuesday, January 31, at noon in NSH 3305<br>
for AI lunch. To learn more about the seminar and lunch, please visit<br>
the AI Lunch webpage <<a href="http://www.cs.cmu.edu/~aiseminar/" rel="noreferrer" target="_blank">http://www.cs.cmu.edu/~<wbr>aiseminar/</a>>.<br>
<br>
On Tuesday, Po-Wei Wang <<a href="http://www.powei.tw/" rel="noreferrer" target="_blank">http://www.powei.tw/</a>> will give a talk titled<br>
?Polynomial optimization methods for matrix factorization?.<br>
<br>
*Abstract:* Matrix factorization is a core technique in many machine<br>
learning problems, yet also presents a nonconvex and often<br>
difficult-to-optimize problem. In this paper we present an approach based<br>
upon polynomial optimization techniques that both improves the convergence<br>
time of matrix factorization algorithms and helps them escape from local<br>
optima. Our method is based on the realization that given a joint search<br>
direction in a matrix factorization task, we can solve the ``subspace<br>
search'' problem (the task of jointly finding the steps to take in each<br>
direction) by solving a bivariate quartic polynomial optimization problem.<br>
We derive two methods for solving this problem based upon sum of squares<br>
moment relaxations and the Durand-Kerner method, then apply these<br>
techniques on matrix factorization to derive a direct coordinate descent<br>
approach and a method for speeding up existing approaches. On three<br>
benchmark datasets we show the method substantially improves convergence<br>
speed over state-of-the-art approaches, while also attaining lower<br>
objective value.<br>
<br>
This is a joint work with Chun-Liang Li and J. Zico Kolter. Forthcoming in<br>
AAAI 2017.<br>
-------------- next part --------------<br>
An HTML attachment was scrubbed...<br>
URL: <<a href="http://mailman.srv.cs.cmu.edu/pipermail/ai-seminar-announce/attachments/20170127/27133949/attachment-0001.html" rel="noreferrer" target="_blank">http://mailman.srv.cs.cmu.<wbr>edu/pipermail/ai-seminar-<wbr>announce/attachments/20170127/<wbr>27133949/attachment-0001.html</a>><br>
<br>
------------------------------<br>
<br>
Subject: Digest Footer<br>
<br>
______________________________<wbr>_________________<br>
ai-seminar-announce mailing list<br>
<a href="mailto:ai-seminar-announce@cs.cmu.edu">ai-seminar-announce@cs.cmu.edu</a><br>
<a href="https://mailman.srv.cs.cmu.edu/mailman/listinfo/ai-seminar-announce" rel="noreferrer" target="_blank">https://mailman.srv.cs.cmu.<wbr>edu/mailman/listinfo/ai-<wbr>seminar-announce</a><br>
<br>
------------------------------<br>
<br>
End of ai-seminar-announce Digest, Vol 70, Issue 5<br>
******************************<wbr>********************<br>
</blockquote></div><br></div>