BEGIN:VCALENDAR
VERSION:2.0
X-WR-CALNAME;VALUE=TEXT:Colloquium Series: Jason Klusowski 
PRODID:-//Harvard events data//EN
BEGIN:VEVENT
UID:event_1636891_0
SUMMARY:Colloquium Series: Jason Klusowski 
DESCRIPTION:<p><span>Our upcoming event for the Statistics Colloquium Series is scheduled for Monday, October 19th from 12:00 – 1:00pm (ET) and will be an in-person&nbsp;presentation at Maxwell-Dworkin, Room 119. Lunch will be provided to guests following the talk. This week's speaker will be Jason Klusowski, Associate Professor in the Department of Operations Research and Financial Engineering (ORFE) at Princeton University.&nbsp;</span></p><p><span><strong>Statistical Attribute Alignment for Black-Box Generative AI</strong></span><br>&nbsp;</p><p><strong>Abstract: </strong><span>Generative AI offers a powerful way to create synthetic data for simulation, training, and evaluation. But what if a model generates outputs with an attribute distribution that differs from what a downstream task requires? For example, medical research may require image collections with specified distributions of demographic groups or disease categories. This talk develops a statistical framework for attribute alignment through output post-processing, using only query access to the generative model. After observing the attributes of generated outputs, we select a batch whose attributes jointly follow a target distribution, exactly or approximately. We develop sampling algorithms and establish their asymptotic optimality in expected model query cost as the desired batch size grows.</span></p><p><strong>Speakers Bio: </strong><a href="https://klusowski.princeton.edu/"><strong>Jason M. Klusowski</strong> </a>is an Associate Professor in the Department of Operations Research and Financial Engineering (ORFE) at Princeton University. He studies the mathematical and statistical foundations of machine learning and AI systems, examining how data, computation, and model structure shape their capabilities and limitations.</p><p>Before joining Princeton, Jason was an Assistant Professor in the Department of Statistics at Rutgers University–New Brunswick. He received his Ph.D. in Statistics and Data Science from Yale University.</p><p>Jason serves on the editorial board of <em>Bernoulli</em>, the journal of the Bernoulli Society. His research is partially supported by a Sloan Research Fellowship in Mathematics and <a href="https://www.nsf.gov/awardsearch/showAward?AWD_ID=2239448"><strong>NSF CAREER DMS-2239448</strong></a>.</p><p>Jason grew up in Winnipeg, in the heart of the Canadian Prairies. His <a href="https://som.yale.edu/faculty-research/faculty-directory/joowon-klusowski"><strong>spouse</strong></a> is an Assistant Professor of Marketing at Yale University.</p>
LOCATION:Maxwell-Dworkin, Room 119
STATUS:CONFIRMED
DTSTART:20261019T160000Z
DTEND:20261019T170000Z
END:VEVENT
END:VCALENDAR