Seminars

We present new theoretical results for procedures identifying coarse structures in a given data set by means of appropriate spectral embeddings. We combine ideas from spectral geometry, metastability, optimal transport, and spectral analysis of weighted graph Laplacians to describe the embedding geometry.

In this talk, we propose an analysis of gradient descent on wide two-layer ReLU neural networks that leads to sharp characterizations of the learned predictor. The main idea is to study the dynamics when the width of the hidden layer goes to infinity, which is a Wasserstein gradient flow.

Deep network approximation is a powerful tool of function approximation via composition. We will present a few new thoughts on deep network approximation from the point of view of scientific computing in practice: given an arbitrary width and depth of neural networks, what is the optimal approximation rate of various function...

Standard machine learning produces models that are highly accurate on average but that degrade dramatically when the test distribtion deviates from the training distribution. While one can train robust models, this often comes at the expense of standard accuracy (on the training distribution).