ROBUST AND EQUITABLE UNCERTAINTY ESTIMATION

Simons Foundation Presidential Lectures

REGISTRATION FOR THIS LECTURE WILL CLOSE THE DAY BEFORE THE EVENT. REVIEW THE COMPLETE LIST OF ENTRANCE REQUIREMENTS BELOW.

Simons Foundation

<h2>Part of the Algorithmic Fairness Presidential Lecture Series in Mathematics and Computer Science.</h2>

Machine learning provides us with an amazing set of tools to make predictions, but how much should we trust particular predictions? To answer this, we need a way of estimating the confidence we should have in particular predictions of black-box models. Standard tools for doing this give guarantees that are averages over predictions. For instance, in a medical application, such tools might paper over poor performance on one medically relevant demographic group if it is made up for by higher performance on another group. Standard methods also depend on the data distribution being static — in other words, the future should be like the past. In this lecture, Aaron Roth will describe a new technique to address both these problems: a way to produce prediction sets for arbitrary black-box prediction methods that have correct empirical coverage even when the data distribution might change in arbitrary, unanticipated ways and such that we have correct coverage even when we zoom in to focus on demographic groups that can be arbitrary and intersecting. <a href="https://www.cis.upenn.edu/~aaroth/" target="_blank" data-msys-clicktrack="0" rel="nofollow noopener noreferrer">Roth</a> is the Henry Salvatori Professor of Computer and Cognitive Science at the University of Pennsylvania. He is co-director of the Networked and Social Systems Engineering (NETS) program. Roth is also an Amazon Scholar at Amazon AWS. He is the recipient of a Presidential Early Career Award for Scientists and Engineers (PECASE) awarded by President Obama in 2016, an Alfred P. Sloan Research Fellowship and an NSF CAREER award. Together with Cynthia Dwork, he is the author of the book “The Algorithmic Foundations of Differential Privacy.” Together with Michael Kearns, he is the author of “The Ethical Algorithm.”To attend this in-person event, you will need to register in advance and provide:<ul><li>Acceptable proof of vaccination (vaccine card/certificate, a copy or photo of vaccine card/certificate or electronic NYS Excelsior Pass or NJ Docket Pass)</li><li>Photo ID</li><li>Eventbrite ticket confirmation email with QR code</li><li>Simons Foundation Health Screening Questionnaire approval email</li></ul>Guests are expected to complete these requirements each time they visit the Simons Foundation and entrance will not be granted without this documentation.On-site registration will not be permitted. Walk-in entry will be denied.SCHEDULEDoors Open: 5:30 p.m.Lecture: 6:00 p.m. – 7:00 p.m.The Gerald D. Fischbach Auditorium complies with the Americans with Disabilities Act and offers accessible seating to visitors with special access needs.

<a href="https://www.simonsfoundation.org/sf-events/?type=simons-foundation-lectures" target="_blank" data-msys-clicktrack="0" rel="nofollow noopener noreferrer">Simons Foundation Presidential Lectures</a> are free public colloquia centered on four main themes: Biology, Physics, Mathematics and Computer Science, and Neuroscience and Autism Science. These curated, high-level scientific talks feature leading scientists and mathematicians and are intended to foster discourse and drive discovery among the broader NYC-area research community. We invite anyone interested in the topic to join us for this weekly lecture series.
<a href="http://eepurl.com/hS7ngv" target="_blank" data-msys-clicktrack="0" rel="nofollow noopener noreferrer">Sign up here</a> to receive Simons Foundation Presidential Lectures announcements and reminders.

Our {communityGuidelinesLink} describe the sort of content we prohibit on Eventbrite. If you suspect an event may be in violation, you can report it to us so we can investigate.

To report other categories of prohibited or illegal content, submit {link}

ROBUST AND EQUITABLE UNCERTAINTY ESTIMATION

More events from Simons Foundation Presidential Lectures

Discover more events from Simons Foundation Presidential Lectures, from Science & Tech to other experiences you might love.

ROBUST AND EQUITABLE UNCERTAINTY ESTIMATION

More events from Simons Foundation Presidential Lectures

Discover more events from Simons Foundation Presidential Lectures, from Science & Tech to other experiences you might love.

You might also like...

Browse more events with different dates, prices, and formats to find your next great experience.