<div dir="ltr">A gentle reminder that the talk will happen tomorrow (Tuesday) noon in NSH 1507.</div><div class="gmail_extra"><br><div class="gmail_quote">On Sat, Sep 30, 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 -- Nihar B. Shah -- October 03<br>
(Adams Wei Yu)<br>
<br>
<br>
------------------------------<wbr>------------------------------<wbr>----------<br>
<br>
Message: 1<br>
Date: Sat, 30 Sep 2017 03:07:09 -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 -- Nihar B. Shah<br>
-- October 03<br>
Message-ID:<br>
<CABzq7eqU0OA2Ekk+<wbr>qf7CmzHmvgZ2mOPSMzPNGzFuinre2=<a href="mailto:RxRA@mail.gmail.com"><wbr>RxRA@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 03, 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, Professor Nihar B. Shah <<a href="http://www.cs.cmu.edu/~nihars/" rel="noreferrer" target="_blank">http://www.cs.cmu.edu/~<wbr>nihars/</a>> will<br>
give the following talk:<br>
<br>
Title: Learning from People<br>
<br>
Abstract: Learning from people represents a new and expanding frontier for<br>
data science. Two critical challenges in this domain are of developing<br>
algorithms for robust learning and designing incentive mechanisms for<br>
eliciting high-quality data. In this talk, I describe progress on these<br>
challenges in the context of two canonical settings, namely those of<br>
ranking and classification. In addressing the first challenge, I introduce<br>
a class of "permutation-based" models that are considerably richer than<br>
classical models, and present algorithms for estimation that are both<br>
rate-optimal and significantly more robust than prior state-of-the-art<br>
methods. I also discuss how these estimators automatically adapt and are<br>
simultaneously also rate-optimal over the classical models, thereby<br>
enjoying a surprising a win-win in the bias-variance tradeoff. As for the<br>
second challenge, I present a class of "multiplicative" incentive<br>
mechanisms, and show that they are the unique mechanisms that can guarantee<br>
honest responses. Extensive experiments on a popular crowdsourcing platform<br>
reveal that the theoretical guarantees of robustness and efficiency indeed<br>
translate to practice, yielding several-fold improvements over prior art.<br>
<br>
Bio: Nihar B. Shah is an Assistant Professor in the Machine Learning and<br>
Computer Science departments at CMU. He is a recipient of the 2017 David J.<br>
Sakrison memorial prize from EECS Berkeley for a "truly outstanding and<br>
innovative PhD thesis", the Microsoft Research PhD Fellowship 2014-16, the<br>
Berkeley Fellowship 2011-13, the IEEE Data Storage Best Paper and Best<br>
Student Paper Awards for the years 2011/2012, and the SVC Aiya Medal 2010.<br>
His research interests include statistics, machine learning, and game<br>
theory, with a current focus on applications to learning from people.<br>
-------------- next part --------------<br>
An HTML attachment was scrubbed...<br>
URL: <<a href="http://mailman.srv.cs.cmu.edu/pipermail/ai-seminar-announce/attachments/20170930/9e1d9b90/attachment-0001.html" rel="noreferrer" target="_blank">http://mailman.srv.cs.cmu.<wbr>edu/pipermail/ai-seminar-<wbr>announce/attachments/20170930/<wbr>9e1d9b90/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 76, Issue 8<br>
******************************<wbr>********************<br>
</blockquote></div><br></div>