35 citations · 107 across the 9 of their papers we have counts for
10 papers · 1 filter
Efficient Gradient Methods for Distributed Saddle Problems
Ruichen Luo, Anton Rodomanov, Sebastian U. Stich
The distributed setting for Saddle Problems (SPs) has recently emerged as a framework for various modern applications in machine learning and multiagent systems. Despite its releva…
Global Complexity Analysis of BFGS
Anton Rodomanov
In this paper, we present a global complexity analysis of the classical BFGS method with inexact line search, as applied to minimizing a strongly convex function with Lipschitz con…
Gradient Methods for Stochastic Optimization in Relative Scale
Yurii Nesterov, Anton Rodomanov
We propose a new concept of a relatively inexact stochastic subgradient and present novel first-order methods that can use such objects to approximately solve convex optimization p…
Subgradient Ellipsoid Method for Nonsmooth Convex Problems
Anton Rodomanov, Yurii Nesterov
In this paper, we present a new ellipsoid-type algorithm for solving nonsmooth problems with convex structure. Examples of such problems include nonsmooth convex minimization probl…
New Results on Superlinear Convergence of Classical Quasi-Newton Methods
Anton Rodomanov, Yurii Nesterov
We present a new theoretical analysis of local superlinear convergence of classical quasi-Newton methods from the convex Broyden class. As a result, we obtain a significant improve…
Rates of superlinear convergence for classical quasi-Newton methods
Anton Rodomanov, Yurii Nesterov
We study the local convergence of classical quasi-Newton methods for nonlinear optimization. Although it was well established a long time ago that asymptotically these methods conv…
Greedy Quasi-Newton Methods with Explicit Superlinear Convergence
Anton Rodomanov, Yurii Nesterov
In this paper, we study greedy variants of quasi-Newton methods. They are based on the updating formulas from a certain subclass of the Broyden family. In particular, this subclass…
Smoothness parameter of power of Euclidean norm
Anton Rodomanov, Yurii Nesterov
In this paper, we study derivatives of powers of Euclidean norm. We prove their Hölder continuity and establish explicit expressions for the corresponding constants. We show that t…
A Randomized Coordinate Descent Method with Volume Sampling
Anton Rodomanov, Dmitry Kropotov
We analyze the coordinate descent method with a new coordinate selection strategy, called volume sampling. This strategy prescribes selecting subsets of variables of certain size p…
Primal-Dual Method for Searching Equilibrium in Hierarchical Congestion Population Games
Pavel Dvurechensky, Alexander Gasnikov, Evgenia Gasnikova +3
In this paper, we consider a large class of hierarchical congestion population games. One can show that the equilibrium in a game of such type can be described as a minimum point i…