skip to main content

H.B. Keller Colloquium

Monday, May 17, 2021
4:30pm to 5:30pm
Add to Cal
Online Event
A Mathematical Perspective of Machine Learning
Weinan E, Professor, Applied Mathematics & Mathematical Physics, Princeton University,

The heart of modern machine learning (ML) is the approximation of high dimensional functions. Traditional approaches, such as approximation by piecewise polynomials, wavelets, or other linear combinations of fixed basis functions, suffer from the curse of dimensionality (CoD). This does not seem to be the case for the neural network-based ML models. To quantify this, we need to develop the corresponding mathematical framework. In this talk, I will report the progress made so far and the main remaining issues within the scope of supervised learning.

I will discuss three major issues: approximation theory and error analysis of modern ML models, qualitative behavior of gradient descent algorithms, and ML from a continuous viewpoint.

For more information, please contact Diana Bohler by phone at 6262326138 or by email at [email protected].