1 citations · 1 across the 6 of their papers we have counts for
7 papers · 1 filter
First-order Optimization Methods with Generalized Smoothness for Low-rank Matrix Factorization
A. V. Bidanets, F. S. Stonyakin
This paper studies several first-order methods for low-rank matrix minimization in the Burer--Monteiro form, where the target matrix is represented as the product of a nonnegative…
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…
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…
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…
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…
Stopping Rules for Gradient Method for Saddle Point Problems with Twoside Polyak-Lojasievich Condition
A. Ya. Muratidi, F. S. Stonyakin
The paper considers approaches to saddle point problems with a two-sided variant of the Polyak-Lojasievich condition based on the gradient method with inexact information and propo…