Nadav Cohen  —  Blog Posts

Does gradient flow over neural networks really represent gradient descent?
Off the Convex Path, Jan’22.

Implicit regularization in tensor factorization: can tensor rank shed light on generalization in deep learning?
Off the Convex Path, Jul’21.

Can implicit regularization in deep learning be explained by norms?
Off the Convex Path, Nov’20.

Understanding implicit regularization in deep learning by analyzing trajectories of gradient descent
Off the Convex Path, Jul’19.

Understanding optimization in deep learning by analyzing trajectories of gradient descent
Off the Convex Path, Nov’18.

Can increasing depth serve to accelerate optimization?
Off the Convex Path, Mar’18.