Statistics and Data Science Seminar - Philippe Rigollet
— 5:00pm
Location:
In Person
-
Posner Hall 151
Speaker:
PHILIPPE RIGOLLET
,
Cecil and Ida Green Distinguished Professor of Mathematics Core Member, Institute for Data, Systems, and Society, Massachusetts Institute of Technology
http://www-math.mit.edu/~rigollet
Since their introduction in 2017, Transformers have revolutionized large language models and the broader field of deep learning. Central to this success is the groundbreaking self-attention mechanism. In this presentation, I’ll introduce a mathematical framework that casts this mechanism as a mean-field interacting particle system, revealing a desirable long-time clustering behavior. This perspective leads to a trove of fascinating questions with unexpected connections to Kuramoto oscillators, sphere packing, Wasserstein gradient flows, and slow dynamics.
—
Philippe Rigollet is the Cecil and Ida Green Distinguished Professor of Mathematics at MIT and a Core Member of the Institute for Data, Systems, and Society. His research explores the foundations of modern machine learning, with a particular focus on optimal transport and the emerging theory of transformer architectures.
For More Information:
mmenk@andrew.cmu.edu