Redirecting to original paper in 30 seconds...

Click below to go immediately or wait for automatic redirect

arxiv_stat_ml 88% Match 1 month ago

Deep Learning as the Disciplined Construction of Tame Objects

generative-ai › autoregressive
📄 Abstract

Abstract: One can see deep-learning models as compositions of functions within the so-called tame geometry. In this expository note, we give an overview of some topics at the interface of tame geometry (also known as o-minimality), optimization theory, and deep learning theory and practice. To do so, we gradually introduce the concepts and tools used to build convergence guarantees for stochastic gradient descent in a general nonsmooth nonconvex, but tame, setting. This illustrates some ways in which tame geometry is a natural mathematical framework for the study of AI systems, especially within Deep Learning.