Zobrazeno 1 - 10
of 727
pro vyhledávání: '"A. A. Gasnikov"'
Second-order methods for convex optimization outperform first-order methods in terms of theoretical iteration convergence, achieving rates up to $O(k^{-5})$ for highly-smooth functions. However, their practical performance and applications are limite
Externí odkaz:
http://arxiv.org/abs/2410.04083
The challenges of black box optimization arise due to imprecise responses and limited output information. This article describes new results on optimizing multivariable functions using an Order Oracle, which provides access only to the order between
Externí odkaz:
http://arxiv.org/abs/2409.11077
Distributed optimization plays an important role in modern large-scale machine learning and data processing systems by optimizing the utilization of computational resources. One of the classical and popular approaches is Local Stochastic Gradient Des
Externí odkaz:
http://arxiv.org/abs/2409.10478
The consensus problem in distributed computing involves a network of agents aiming to compute the average of their initial vectors through local communication, represented by an undirected graph. This paper focuses on the studying of this problem usi
Externí odkaz:
http://arxiv.org/abs/2409.00605
In this paper, we consider a dynamic equilibrium transportation problem. There is a fixed number of cars moving from origin to destination areas. Preferences for arrival times are expressed as a cost of arriving before or after the preferred time at
Externí odkaz:
http://arxiv.org/abs/2408.17196
Autor:
Pichugin, Alexander, Pechin, Maksim, Beznosikov, Aleksandr, Novitskii, Vasilii, Gasnikov, Alexander
Variational inequalities are a universal optimization paradigm that incorporate classical minimization and saddle point problems. Nowadays more and more tasks require to consider stochastic formulations of optimization problems. In this paper, we pre
Externí odkaz:
http://arxiv.org/abs/2408.06728
Recommender systems aim to estimate the dynamically changing user preferences and sequential dependencies between historical user behaviour and metadata. Although transformer-based models have proven to be effective in sequential recommendations, the
Externí odkaz:
http://arxiv.org/abs/2408.05606
In this paper, we propose universal proximal mirror methods to solve the variational inequality problem with Holder continuous operators in both deterministic and stochastic settings. The proposed methods automatically adapt not only to the oracle's
Externí odkaz:
http://arxiv.org/abs/2407.17519
Autor:
Yarmoshik, Demyan, Rogozin, Alexander, Kiselev, Nikita, Dorin, Daniil, Gasnikov, Alexander, Kovalev, Dmitry
We consider the decentralized minimization of a separable objective $\sum_{i=1}^{n} f_i(x_i)$, where the variables are coupled through an affine constraint $\sum_{i=1}^n\left(\mathbf{A}_i x_i - b_i\right) = 0$. We assume that the functions $f_i$, mat
Externí odkaz:
http://arxiv.org/abs/2407.02020
Autor:
Nazykov, Ruslan, Shestakov, Aleksandr, Solodkin, Vladimir, Beznosikov, Aleksandr, Gidel, Gauthier, Gasnikov, Alexander
The Conditional Gradient (or Frank-Wolfe) method is one of the most well-known methods for solving constrained optimization problems appearing in various machine learning tasks. The simplicity of iteration and applicability to many practical problems
Externí odkaz:
http://arxiv.org/abs/2406.06788