On the global convergence of gradient flow for wide shallow models beyond homogeneous nonlinearities

Organisé par

Institut Henri Poincaré

A surprising phenomenon in the training of neural networks is the ability of gradient descent to find global minimizers of the training loss despite its non-convexity. Following earlier work, we investigate this behavior for wide shallow models. Existing global convergence results primarily concern models with positively one-homogeneous nonlinearities, such as ReLU activations, and models with sca

Vérifie les horaires sur la page officielle avant de te déplacer.