UCB, wherein agents cooperatively minimize the group regret under the coordination of a central server.

Cohen et al. (2021) empirically study the evolution of the largest eigenvalue of the loss Hessian, also known as sharpness, along the gradient descent (GD) trajectory and observe the Edge of Stability (EoS) phenomenon.

Our analysis highlights sufficient properties for a regret minimization algorithm to be used as leader.

Recently, there has been a marked increase in interest regarding the generalization capabilities of unregularized gradient-based learning methods.

The most forceful driver of advancements in the field of Machine Learning over the past decades has been the success of deep neural networks.