Principal Investigator Alexander Rakhlin
We study the problem of building a good predictor based on an i.i.d. sample. While much is understood in this classical setting, our current focus is on the Deep Learning models. In particular, we study the various measures of complexity of neural networks that govern their out-of-sample performance. We aim to understand the "geometry" (in an appropriate sense) of neural networks and its relation to the prediction ability of trained models.