6 papers · 1 filter
Simple Stepsize for Quasi-Newton Methods with Global Convergence Guarantees
Artem Agafonov, Vladislav Ryspayev, Samuel Horváth +3
Quasi-Newton methods are widely used for solving convex optimization problems due to their ease of implementation, practical efficiency, and strong local convergence guarantees. Ho…
OPTAMI: Global Superlinear Convergence of High-order Methods
Dmitry Kamzolov, Dmitry Pasechnyuk, Artem Agafonov +2
Second-order methods for convex optimization outperform first-order methods in terms of theoretical iteration convergence, achieving rates up to for highly-smooth funct…
An Accelerated Second-Order Method for Distributed Stochastic Optimization
Artem Agafonov, Pavel Dvurechensky, Gesualdo Scutari +4
We consider distributed stochastic optimization problems that are solved with master/workers computation architecture. Statistical arguments allow to exploit statistical similarity…
Lower bounds for conditional gradient type methods for minimizing smooth strongly convex functions
Artem Agafonov
In this paper, we consider conditional gradient methods. These are methods that use a linear minimization oracle, which, for a given vector , computes the solut…
Gradient Methods for Problems with Inexact Model of the Objective
Fedor Stonyakin, Darina Dvinskikh, Pavel Dvurechensky +8
We consider optimization methods for convex minimization problems under inexact information on the objective function. We introduce inexact model of the objective, which as a parti…
Inexact Model: A Framework for Optimization and Variational Inequalities
Fedor Stonyakin, Alexander Gasnikov, Alexander Tyurin +6
In this paper we propose a general algorithmic framework for first-order methods in optimization in a broad sense, including minimization problems, saddle-point problems and variat…