6 papers
Frank-Wolfe Algorithms for (L0, L1)-smooth functions
A. A. Vyguzov, F. S. Stonyakin
We propose a new version of the Frank-Wolfe method, called the (L0, L1)-Frank-Wolfe algorithm, developed for optimization problems with (L0, L1)-smooth objectives. We establish tha…
On Solving Minimization and Min-Max Problems by First-Order Methods with Relative Error in Gradients
Artem Vasin, Valery Krivchenko, Dmitry Kovalev +6
First-order methods for minimization and saddle point (min-max) problems are widely used for solving large-scale problems, in particular arising in machine learning. The majority o…
A Fully Adaptive Frank-Wolfe Algorithm for Relatively Smooth Problems and Its Application to Centralized Distributed Optimization
A. A. Vyguzov, F. S. Stonyakin
We study the Frank-Wolfe algorithm for constrained optimization problems with relatively smooth objectives. Building upon our previous work, we propose a fully adaptive variant of…
About some works of Boris Polyak on convergence of gradient methods and their development
Seydamet Ablaev, Aleksandr Beznosikov, Alexander Gasnikov +4
The paper presents a review of the state-of-the-art of subgradient and accelerated methods of convex optimization, including in the presence of disturbances and access to various i…
On quasi-convex smooth optimization problems by a comparison oracle
A. V. Gasnikov, M. S. Alkousa, A. V. Lobanov +4
Frequently, when dealing with many machine learning models, optimization problems appear to be challenging due to a limited understanding of the constructions and characterizations…
Accelerated Bregman gradient methods for relatively smooth and relatively Lipschitz continuous minimization problems
O. S. Savchuk, M. S. Alkousa, A. S. Shushko +4
In this paper, we propose some accelerated methods for solving optimization problems under the condition of relatively smooth and relatively Lipschitz continuous functions with an…