Classical analysis of convex and non-convex optimization methods often
r...
In this paper, we provide a rigorous proof of convergence of the Adaptiv...
Gradient clipping is a standard training technique used in deep learning...
Despite the established convergence theory of Optimistic Gradient Descen...
In this paper, we study a linear bandit optimization problem in a federa...
It is a well-known fact that nonconvex optimization is computationally
i...
We provide a first-order oracle complexity lower bound for finding stati...
Neural networks are vulnerable to adversarial examples, i.e. inputs that...
Gradient descent finds a global minimum in training deep neural networks...