66 citations · 450 across the 76 of their papers we have counts for
13 papers · 1 filter
Hessian barrier algorithms for non-convex conic optimization
Pavel Dvurechensky, Mathias Staudigl
We consider the minimization of a continuous function over the intersection of a regular cone with an affine set via a new class of adaptive first- and second-order optimization me…
Stochastic optimization for dynamic pricing
Dmitry Pasechnyuk, Pavel Dvurechensky, Sergey Omelchenko +1
We consider the problem of supply and demand balancing that is stated as a minimization problem for the total expected revenue function describing the behavior of both consumers an…
Decentralized Local Stochastic Extra-Gradient for Variational Inequalities
Aleksandr Beznosikov, Pavel Dvurechensky, Anastasia Koloskova +3
We consider distributed stochastic variational inequalities (VIs) on unbounded domains with the problem data that is heterogeneous (non-IID) and distributed across many devices. We…
High Probability Complexity Bounds for Non-Smooth Stochastic Optimization with Heavy-Tailed Noise
Eduard Gorbunov, Marina Danilova, Innokentiy Shibaev +2
Stochastic first-order methods are standard for training large-scale machine learning models. Random behavior may cause a particular run of an algorithm to result in a highly subop…
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…
An Accelerated Method For Decentralized Distributed Stochastic Optimization Over Time-Varying Graphs
Alexander Rogozin, Mikhail Bochko, Pavel Dvurechensky +2
We consider a distributed stochastic optimization problem that is solved by a decentralized network of agents with only local communication between neighboring agents. The goal of…
On Accelerated Methods for Saddle-Point Problems with Composite Structure
Vladislav Tominin, Yaroslav Tominin, Ekaterina Borodich +3
We consider strongly-convex-strongly-concave saddle-point problems with general non-bilinear objective and different condition numbers with respect to the primal and the dual varia…
Solving smooth min-min and min-max problems by mixed oracle algorithms
Egor Gladin, Abdurakhmon Sadiev, Alexander Gasnikov +3
In this paper, we consider two types of problems that have some similarity in their structure, namely, min-min problems and min-max saddle-point problems. Our approach is based on…
Hyperfast Second-Order Local Solvers for Efficient Statistically Preconditioned Distributed Optimization
Pavel Dvurechensky, Dmitry Kamzolov, Aleksandr Lukashevich +4
Statistical preconditioning enables fast methods for distributed large-scale empirical risk minimization problems. In this approach, multiple worker nodes compute gradients in para…
Decentralized Distributed Optimization for Saddle Point Problems
Alexander Rogozin, Aleksandr Beznosikov, Darina Dvinskikh +3
We consider distributed convex-concave saddle point problems over arbitrary connected undirected networks and propose a decentralized distributed algorithm for their solution. The…
Newton Method over Networks is Fast up to the Statistical Precision
Amir Daneshmand, Gesualdo Scutari, Pavel Dvurechensky +1
We propose a distributed cubic regularization of the Newton method for solving (constrained) empirical risk minimization problems over a network of agents, modeled as undirected gr…
Accelerated gradient methods with absolute and relative noise in the gradient
Vasin Artem, Alexander Gasnikov, Pavel Dvurechensky +1
In this paper, we investigate accelerated first-order methods for smooth convex optimization problems under inexact information on the gradient of the objective. The noise in the g…
First-Order Methods for Convex Optimization
Pavel Dvurechensky, Mathias Staudigl, Shimrit Shtern
First-order methods for solving convex optimization problems have been at the forefront of mathematical optimization in the last 20 years. The rapid development of this important c…