[AI Seminar] ai-seminar-announce Digest, Vol 78, Issue 5

[Adams Wei Yu]

A gentle reminder that the talk will happen tomorrow (Tuesday) noon.

On Sun, Nov 19, 2017 at 9:00 AM, <ai-seminar-announce-request at cs.cmu.edu>
wrote:

> Send ai-seminar-announce mailing list submissions to
>         ai-seminar-announce at cs.cmu.edu
>
> To subscribe or unsubscribe via the World Wide Web, visit
>         https://mailman.srv.cs.cmu.edu/mailman/listinfo/ai-
> seminar-announce
> or, via email, send a message with subject or body 'help' to
>         ai-seminar-announce-request at cs.cmu.edu
>
> You can reach the person managing the list at
>         ai-seminar-announce-owner at cs.cmu.edu
>
> When replying, please edit your Subject line so it is more specific
> than "Re: Contents of ai-seminar-announce digest..."
>
>
> Today's Topics:
>
>    1.  AI Seminar sponsored by Apple -- Vaishnavh Nagarajan     -- Nov
>       21 (Adams Wei Yu)
>
>
> ----------------------------------------------------------------------
>
> Message: 1
> Date: Sun, 19 Nov 2017 05:46:06 -0800
> From: Adams Wei Yu <weiyu at cs.cmu.edu>
> To: ai-seminar-announce at cs.cmu.edu
> Cc: Vaishnavh Nagarajan <vaishnavh.nagarajan at gmail.com>
> Subject: [AI Seminar] AI Seminar sponsored by Apple -- Vaishnavh
>         Nagarajan       -- Nov 21
> Message-ID:
>         <CABzq7ertCO5ccBL7_h_8d6zzV6MZCQOiu5idosiMg4Y7ytPs3
> Q at mail.gmail.com>
> Content-Type: text/plain; charset="utf-8"
>
> Dear faculty and students,
>
> We look forward to seeing you next Tuesday, Nov 21, at noon in NSH 3305 for
> AI Seminar sponsored by Apple. To learn more about the seminar series,
> please visit the AI Seminar webpage <http://www.cs.cmu.edu/~aiseminar/>.
>
> On Tuesday, Vaishnavh Nagarajan
> <http://www.cs.cmu.edu/~vaishnan/home/index.html> will give the following
> talk:
>
> Title: Gradient Descent GANs are locally stable
>
> Abstract:
>
> Generative modeling, a core problem in unsupervised learning, aims at
> understanding data by learning a model that can generate datapoints that
> resemble the real-world distribution. Generative Adversarial Networks
> (GANs) are an increasingly popular framework that solve this by optimizing
> two deep networks, a "discriminator" and a "generator", in tandem.
>
> However, this complex optimization procedure is still poorly understood.
> More specifically, it was not known whether equilibrium points of this
> system are "locally asymptotically stable" i.e., when initialized
> sufficiently close to an equilibrium point, does the optimization procedure
> converge to that point? In this work, we analyze the "gradient descent"
> form of GAN optimization (i.e., the setting where we simultaneously take
> small gradient steps in both generator and discriminator parameters). We
> show that even though GAN optimization does not correspond to a
> convex-concave game, even for simple parameterizations, under proper
> conditions, its equilibrium points are still locally asymptotically stable.
> On the other hand, we show that for the recently-proposed Wasserstein GAN
> (WGAN), the optimization procedure might cycle around an equilibrium point
> without ever converging to it. Finally, motivated by this stability
> analysis, we propose an additional regularization term for GAN updates,
> which can guarantee local stability for both the WGAN and for the
> traditional GAN. Our regularizer also shows practical promise in speeding
> up convergence and in addressing a well-known failure mode in GANs called
> mode collapse.
> -------------- next part --------------
> An HTML attachment was scrubbed...
> URL: <http://mailman.srv.cs.cmu.edu/pipermail/ai-seminar-
> announce/attachments/20171119/e9f7ac27/attachment-0001.html>
>
> ------------------------------
>
> Subject: Digest Footer
>
> _______________________________________________
> ai-seminar-announce mailing list
> ai-seminar-announce at cs.cmu.edu
> https://mailman.srv.cs.cmu.edu/mailman/listinfo/ai-seminar-announce
>
> ------------------------------
>
> End of ai-seminar-announce Digest, Vol 78, Issue 5
> **************************************************
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/ai-seminar-announce/attachments/20171120/8b0f2fea/attachment.html>