<div dir="ltr">A gentle reminder that the talk will happen tomorrow (Tuesday) noon at NSH 1507.</div><div class="gmail_extra"><br><div class="gmail_quote">On Sun, Oct 8, 2017 at 9:00 AM,  <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 Seminar sponsored by Apple -- Chun-Liang Li --        October 10<br>
      (Adams Wei Yu)<br>
<br>
<br>
------------------------------<wbr>------------------------------<wbr>----------<br>
<br>
Message: 1<br>
Date: Sat, 7 Oct 2017 16:18:31 -0700<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 Seminar sponsored by Apple -- Chun-Liang Li<br>
        --      October 10<br>
Message-ID:<br>
        <<a href="mailto:CABzq7erc-_U2G4PyYaLdB0QaZsgyJBP2r8BaDKjPzRvGiKYZYw@mail.gmail.com">CABzq7erc-_<wbr>U2G4PyYaLdB0QaZsgyJBP2r8BaDKjP<wbr>zRvGiKYZYw@mail.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, October 10, at noon in NSH 1507<br>
(unusual place) for AI Seminar sponsored by Apple. To learn more about the<br>
seminar series, please visit the AI Seminar webpage<br>
<<a href="http://www.cs.cmu.edu/~aiseminar/" rel="noreferrer" target="_blank">http://www.cs.cmu.edu/~<wbr>aiseminar/</a>>.<br>
<br>
On Tuesday, Chun-Liang Li <<a href="http://www.cs.cmu.edu/~chunlial/" rel="noreferrer" target="_blank">http://www.cs.cmu.edu/~<wbr>chunlial/</a>> will give the<br>
following talk:<br>
<br>
Title: MMD GAN: Towards Deeper Understanding of Moment Matching Network<br>
<br>
Abstract:<br>
<br>
Generative moment matching network (GMMN) is a deep generative model that<br>
differs from Generative Adversarial Network (GAN) by replacing the<br>
discriminator in GAN with a two-sample test based on kernel maximum mean<br>
discrepancy (MMD). Although some theoretical guarantees of MMD have been<br>
studied, the empirical performance of GMMN is still not as competitive as<br>
that of GAN on challenging and large benchmark datasets. The computational<br>
efficiency of GMMN is also less desirable in comparison with GAN, partially<br>
due to its requirement for a rather large batch size during the training.<br>
In this paper, we propose to improve both the model expressiveness of GMMN<br>
and its computational efficiency by introducing adversarial kernel learning<br>
techniques, as the replacement of a fixed Gaussian kernel in the original<br>
GMMN. The new approach combines the key ideas in both GMMN and GAN, hence<br>
we name it MMD-GAN. The new distance measure in MMD-GAN is a meaningful<br>
loss that enjoys the advantage of weak topology and can be optimized via<br>
gradient descent with relatively small batch sizes. In our evaluation on<br>
multiple benchmark datasets, including MNIST, CIFAR- 10, CelebA and LSUN,<br>
the performance of MMD-GAN significantly outperforms GMMN, and is<br>
competitive with other representative GAN works.<br>
-------------- next part --------------<br>
An HTML attachment was scrubbed...<br>
URL: <<a href="http://mailman.srv.cs.cmu.edu/pipermail/ai-seminar-announce/attachments/20171007/11fd61d9/attachment-0001.html" rel="noreferrer" target="_blank">http://mailman.srv.cs.cmu.<wbr>edu/pipermail/ai-seminar-<wbr>announce/attachments/20171007/<wbr>11fd61d9/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 77, Issue 2<br>
******************************<wbr>********************<br>
</blockquote></div><br></div>