Gradient Descent on Infinitely Wide Neural Networks: Global Convergence and Generalization [article]

Francis Bach
2021 arXiv   pre-print
Many supervised machine learning methods are naturally cast as optimization problems. For prediction models which are linear in their parameters, this often leads to convex problems for which many mathematical guarantees exist. Models which are non-linear in their parameters such as neural networks lead to non-convex optimization problems for which guarantees are harder to obtain. In this review paper, we consider two-layer neural networks with homogeneous activation functions where the number
more » ... f hidden neurons tends to infinity, and show how qualitative convergence guarantees may be derived.
arXiv:2110.08084v1 fatcat:stye5jkm5fhyjiclvmz6olxtly