IMPALA: scalable distributed deep-rl with importance weighted actor-learner architectures.69

CuLE is available at https://github.com/NVlabs/cule.

We consider linear prediction with a convex Lipschitz loss, or more generally, stochastic convex optimization problems of generalized linear form, i.e.

To this end, we follow Ainsworth et al.

Toourknowledge, ADASPIDER isthefirstparameterfree non-convex variance-reduction method in the sense that it does not require the knowledge of problem-dependent parameters, such as smoothness constant L,targetaccuracyϵoranybound ongradient norms.

Much of the work in online learning focuses on the study of sublinear upper bounds on the regret.

This paper will focus on the case of graph classification, but with minor modifications, our framework can beextended toother tasks ofinterest.