Statistical Physics of Machine Learning

  • Speaker
  • Lenka Zdeborová, Ph.D.Professor of Physics and of Computer Science, École Polytechnique
Date & Time


Gerald D. Fischbach Auditorium
160 5th Ave
New York, NY 10010 United States

View Map

Doors open: 5:30 p.m. (No entrance before 5:30 p.m.)

Lecture: 6:00 p.m. – 7:00 p.m. (Admittance closes at 6:20 p.m.)

Invitation Only

The 2024 lecture series in mathematics and computer science is “Machine Learning in the Natural Sciences.” Machine learning has become a transformative tool for advancing science. In these lectures, scientists will discuss their use of machine learning in everything from biology and oceanography to astrophysics and particle physics. These applications are sparking discoveries while also helping scientists uncover what the tools are actually gleaning from data.
2024 Lecture Series Themes

Biology: Dynamics of Life

Mathematics and Computer Science: Machine Learning in the Natural Sciences

Neuroscience and Autism Science: The Social Brain

Physics: Atmospheres: Earth to Exoplanets

About Presidential Lectures

Presidential Lectures 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 those interested in the topic to join us for this weekly lecture series.

Machine learning provides an invaluable toolbox for the natural sciences, but it also comes with many open questions that the theoretical branches of the natural sciences can investigate.

In this Presidential Lecture, Lenka Zdeborová will describe recent trends and progress in exploring questions surrounding machine learning. She will discuss how diffusion or flow-based generative models sample (or fail to sample) challenging probability distributions. She will present a toy model of dot-product attention that presents a phase transition between positional and semantic learning. She will also revisit some classical methods for estimating uncertainty and their status in the context of modern overparameterized neural networks.

About the Speaker

Zdeborová is a professor of physics and computer science at École Polytechnique Fédérale de Lausanne, where she leads the Statistical Physics of Computation Laboratory. From 2010 to 2020, she was a researcher at the French National Centre for Scientific Research (CNRS), working at the Institute of Theoretical Physics at CEA Paris-Saclay. Zdeborová’s expertise is in applying concepts from statistical physics to problems in machine learning, signal processing, inference and optimization. She enjoys erasing the boundaries between theoretical physics, mathematics and computer science.

Advancing Research in Basic Science and MathematicsSubscribe to our newsletters to receive news & updates