Accelerated Convex Optimization with Stochastic Gradients: Generalizing the Strong-Growth Condition
From MaRDI portal
Abstract: This paper presents a sufficient condition for stochastic gradients not to slow down the convergence of Nesterov's accelerated gradient method. The new condition has the strong-growth condition by Schmidt & Roux as a special case, and it also allows us to (i) model problems with constraints and (ii) design new types of oracles (e.g., oracles for finite-sum problems such as SAGA). Our results are obtained by revisiting Nesterov's accelerated algorithm and are useful for designing stochastic oracles without changing the underlying first-order method.
This page was built for publication: Accelerated Convex Optimization with Stochastic Gradients: Generalizing the Strong-Growth Condition
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6405878)
