BEGIN:VCALENDAR
VERSION:2.0
X-WR-CALNAME;VALUE=TEXT:Harvard AI, Math, and Statistics Seminar: Claire Boyer 
PRODID:-//Harvard events data//EN
BEGIN:VEVENT
UID:event_1636921_0
SUMMARY:Harvard AI, Math, and Statistics Seminar: Claire Boyer 
DESCRIPTION:<p><span>Our upcoming event for the Harvard AI, Math, and Statistics Seminars is scheduled for Friday, October 9th from 10:30 – 11:30pm (ET) and will be an in-person&nbsp;presentation at Maxwell-Dworkin, Room 134 a/b. This week's speaker will be <strong>Claire Boyer, Professor at Paris-Saclay university in the Laboratoire de Mathématiques d'Orsay</strong></span></p><p><strong>How attention learns structure from data?</strong></p><p>&nbsp;</p><p>Transformer architectures have demonstrated remarkable empirical success, yet their ability to extract statistical structure from data remains only partially understood. In this talk, I will present recent work shedding light on attention mechanisms through a statistical and operator-theoretic lens.</p><p>Based on large-prompt asymptotics, one can show that softmax attention converges to a linear operator acting on the input-token distribution under Gaussian assumptions. This regime enables a precise analysis of both the outputs and the training dynamics using concentration arguments, revealing a surprising bridge between nonlinear softmax attention and tractable linear models.</p><p>These results suggest that attention can be understood as a flexible statistical operator that adapts to the underlying data distribution, providing a unifying framework to study its role in representation learning and in-context inference. I will conclude by discussing the connections between transformer architectures and principal component analysis, using this setting to illustrate the power of concentration methods in high-dimensional statistics.</p>
LOCATION:Maxwell-Dworkin 134A/B
STATUS:CONFIRMED
DTSTART:20261009T143000Z
DTEND:20261009T153000Z
END:VEVENT
END:VCALENDAR