Accelerated meta-algorithm for convex optimization
arXiv:2004.08691 · doi:10.1134/S096554252101005X
Abstract
We propose an accelerated meta-algorithm, which allows to obtain accelerated methods for convex unconstrained minimization in different settings. As an application of the general scheme we propose nearly optimal methods for minimizing smooth functions with Lipschitz derivatives of an arbitrary order, as well as for smooth minimax optimization problems. The proposed meta-algorithm is more general than the ones in the literature and allows to obtain better convergence rates and practical performance in several settings.
arXiv comment25 pages, in Russian
References in corpus (8)
- Contracting Proximal Methods for Smooth Convex Optimization
- The global rate of convergence for optimal tensor methods in smooth convex optimization
- Catalyst Acceleration for First-order Convex Optimization: from Theory to Practice
- On Inexact Solution of Auxiliary Problems in Tensor Methods for Convex Optimization
- Near-Optimal Hyperfast Second-Order Method for convex optimization and its Sliding
- Accelerated methods for composite non-bilinear saddle point problem
- Accuracy of Gaussian approximation in nonparametric Bernstein -- von Mises Theorem
- Accelerated and nonaccelerated stochastic gradient descent with model conception