<!DOCTYPE html>
<html>
  <head>

    <meta http-equiv="content-type" content="text/html; charset=UTF-8">
  </head>
  <body>
    *Speaker:* Sinan Yildirim (Sabancı Üniversitesi)<br>
    *Date:* 10.11.2024<br>
    *Time:* 15:00 - 16:00<br>
    *Location:* Galatasaray Üniversitesi, Ortaköy, Çırağan Cd. No:36,
    34349 Beşiktaş,H 306<br>
    <br>
    <br>
    *Title: Adaptive Online Bayesian Estimation of Frequency
    Distributions with Local Differential Privacy *<br>
    <br>
    *Abstract:* We propose a novel Bayesian approach for the adaptive
    and online estimation of the frequency distribution of a finite
    number of categories under the local differential privacy (LDP)
    framework. The proposed algorithm performs Bayesian parameter
    estimation via posterior sampling and adapts the randomization
    mechanism for LDP based on the obtained posterior samples. We
    propose a randomized mechanism for LDP which uses a subset of
    categories as an input and whose performance depends on the selected
    subset and the true frequency distribution. By using the posterior
    sample as an estimate of the frequency distribution, the algorithm
    performs a computationally tractable subset selection step to
    maximize the utility of the privatized response of the next user. We
    propose several utility functions related to well-known information
    metrics, such as (but not limited to) Fisher information matrix,
    total variation distance, and information entropy. We compare each
    of these utility metrics in terms of their computational complexity.
    We employ stochastic gradient Langevin dynamics for posterior
    sampling, a computationally efficient approximate Markov chain Monte
    Carlo method. We provide a theoretical analysis showing that (i) the
    posterior distribution targeted by the algorithm converges to the
    true parameter even for approximate posterior sampling, and (ii) the
    algorithm selects the optimal subset with high probability if
    posterior sampling is performed exactly. We also provide numerical
    results that empirically demonstrate the estimation accuracy of our
    algorithm where we compare it with non-adaptive and semi-adaptive
    approaches under experimental settings with various combinations of
    privacy parameters and population distribution parameters.<br>
    <br>
    *(joint w. Soner Aydın)*<br>
    <br>
    <br>
    * To access to the complete seminar calendar please visit this link<br>
<a class="moz-txt-link-rfc2396E" href="https://calendar.google.com/calendar/embed?src=mathseminar%40galatasaray.education&ctz=Europe%2FIstanbul&mode=AGENDA&showTitle=0&showNav=0&showDate=0&showPrint=0&showTabs=0&showCalendars=0&showTz=0&showDetails=1%22%20style=%22border:%200%22%20width=%22450%22%20height=%22600%22%20frameborder=%220%22%20scrolling=%22yes%22"><https://calendar.google.com/calendar/embed?src=mathseminar%40galatasaray.education&ctz=Europe%2FIstanbul&mode=AGENDA&showTitle=0&showNav=0&showDate=0&showPrint=0&showTabs=0&showCalendars=0&showTz=0&showDetails=1%22%20style=%22border:%200%22%20width=%22450%22%20height=%22600%22%20frameborder=%220%22%20scrolling=%22yes%22></a> and<br>
    to add to your calendar use ical url.<br>
<a class="moz-txt-link-rfc2396E" href="https://calendar.google.com/calendar/ical/mathseminar%40galatasaray.education/public/basic.ics"><https://calendar.google.com/calendar/ical/mathseminar%40galatasaray.education/public/basic.ics></a><br>
    * Participants from outside Galatasaray Üniversitesi are kindly<br>
    requested to send an email to <a class="moz-txt-link-abbreviated" href="mailto:mathseminar@galatasaray.education">mathseminar@galatasaray.education</a><br>
    before 13:00 on the day of the seminar.<br>
    <br>
    ---<br>
    Galatasaray Üniversitesi Matematik Bölümü<br>
    <br>
    <a class="moz-txt-link-freetext" href="https://matematik.gsu.edu.tr/tr/arastirma/seminerler">https://matematik.gsu.edu.tr/tr/arastirma/seminerler</a><br>
    <br>
    <a class="moz-txt-link-rfc2396E" href="https://matematik.gsu.edu.tr/"><https://matematik.gsu.edu.tr/></a><br>
    <br>
    <br>
    <br>
    <br>
    <div id="grammalecte_menu_main_button_shadow_host"
      style="width: 0px; height: 0px;"></div>
  </body>
</html>