On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport

This is an idealization of the usual way to train neural networks with a large hidden layer.

Feb-13-2026, 23:41:35 GMT

Title
On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport
On the Global Convergence of Gradient Descent for Over-parameterized Models using Optimal Transport

Title	Similarity	Source
None found