Currently, most theoretical works on implicit regularisation have primarily focused on continuous time approximations of (S)GD where the impact of crucial hyperparameters such as the stepsize and the minibatch size are ignored. One such common simplification is to analyse gradient flow, which is a continuous time limit of GD and minibatch SGD with an infinitesimal stepsize. By definition, this analysis does not capture the effect of stepsize or stochasticity.

Textual network embedding leverages rich text information associated with the network to learn low-dimensional vectorial representations of vertices.

Neural Information Processing Systems http://nips.cc/

In this paper, we consider various tree constructions and examine how the choice of parameters affects the generalization error of the resulting random forests as the sample size goes to infinity.

We consider learning problems in which examples are dependent and their dependency relation is characterized by a graph.

Inparticular,foreach task at testing time, theclasses effectivelypresent intheunlabeled query setareknown a priori, and correspond exactly to the set of classes represented in the labeled supportset.

In this paper we consider linearly constrained stochastic approximation problems with federated learning asaspecial case.

In this paper we consider linearly constrained stochastic approximation problems with federated learning asaspecial case.

Neural Information Processing Systems http://nips.cc/