[math-ias] Announcement: Rutgers NHETC Seminar on Tuesday, March 7 at 2:30pm - 385E and Zoom - "Null Hypothesis Test for Anomaly Detection" - Manuel Szewc, University of Cincinnati

[Lisa Fleischer]

-------- Forwarded Message --------
Subject: 	Rutgers NHETC Seminar on Tuesday, March 7 at 2:30pm - 385E and 
Zoom
Date: 	Fri, 3 Mar 2023 19:33:55 +0000
From: 	Christina Pettola <cpettola at physics.rutgers.edu>
To: 	allnhetc at lists.physics.rutgers.edu 
<allnhetc at lists.physics.rutgers.edu>, Ananda Roy 
<ananda.roy at physics.rutgers.edu>, lisa <lisa at ias.edu>
CC: 	szewcml at ucmail.uc.edu <szewcml at ucmail.uc.edu>



Good afternoon,

Our seminar next Tuesday, March 7 at 2:30 PM with Dr. Manuel Szewc 
<https://inspirehep.net/authors/1800706> (University of Cincinnati) will 
be held in*385Eand on Zoom*.


Below are the Zoom details:

    Join Zoom Meeting

    https://rutgers.zoom.us/j/94699297301?pwd=SVJieHRUYUtmZmRCbGZKQlBTMTRPdz09
    <https://rutgers.zoom.us/j/94699297301?pwd=SVJieHRUYUtmZmRCbGZKQlBTMTRPdz09>

    Join by SIP

    94699297301 at zoomcrc.com

    Meeting ID: 946 9929 7301

    Password: nhetc

    One tap mobile

    +13126266799,,94699297301# US (Chicago)

    +16465588656,,94699297301# US (New York)

    Join By Phone

             +1 312 626 6799 US (Chicago)

             +1 646 558 8656 US (New York)

             +1 301 715 8592 US (Washington DC)

             +1 346 248 7799 US (Houston)

             +1 669 900 9128 US (San Jose)

             +1 253 215 8782 US (Tacoma)

    Meeting ID: 946 9929 7301

    Find your local number:https://rutgers.zoom.us/u/abhpza0TGi
    <https://rutgers.zoom.us/u/abhpza0TGi>

Here are the seminar details:

    _*Title:*_ Null Hypothesis Test for Anomaly Detection

    _*Abstract:*_
    In this talk we present a hypothesis test designed to exclude
    thebackground-only hypothesis for Anomaly detection searchs.
    Extending ClassificationWithout Labels, we show that by testing for
    statistical independence of the twodiscriminating dataset regions,
    we are able exclude the background-onlyhypothesis without relying on
    fixed anomaly score cuts or extrapolations ofbackground estimates
    between regions. The method relies on the assumption ofconditional
    independence of anomaly score features and dataset regions, whichcan
    be ensured using existing decorrelation techniques. As a benchmark
    example,we consider the LHC Olympics dataset where we show that
    mutual informationrepresents a suitable test for statistical
    independence and our method exhibitsexcellent and robust performance
    at different signal fractions even in presenceof realistic feature
    correlations.

    **

Thank you and have a great weekend!

Sincerely,

Christina

---

Christina Pettola

Administrative Assistant
New High Energy Theory Center
Rutgers, The State University of New Jersey
*Please email if you need to reach me: cpettola at physics.rutgers.edu 
<mailto:cpettola at physics.rutgers.edu>*
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://imap.math.ias.edu/pipermail/all/attachments/20230303/db1b5b7c/attachment-0001.html>