3 citations · 10 across the 19 of their papers we have counts for
6 papers · 1 filter
About some works of Boris Polyak on convergence of gradient methods and their development
Seydamet Ablaev, Aleksandr Beznosikov, Alexander Gasnikov +4
The paper presents a review of the state-of-the-art of subgradient and accelerated methods of convex optimization, including in the presence of disturbances and access to various i…
The Black-Box Optimization Problem: Zero-Order Accelerated Stochastic Method via Kernel Approximation
Aleksandr Lobanov, Nail Bashirov, Alexander Gasnikov
In this paper, we study the standard formulation of an optimization problem when the computation of gradient is not available. Such a problem can be classified as a "black box" opt…
Convergence analysis of stochastic gradient descent with adaptive preconditioning for non-convex and convex functions
Dmitrii A. Pasechnyuk, Alexander Gasnikov, Martin Takáč
Preconditioning is a crucial operation in gradient-based numerical optimisation. It helps decrease the local condition number of a function by appropriately transforming its gradie…
Accelerated Zero-Order SGD Method for Solving the Black Box Optimization Problem under "Overparametrization" Condition
Aleksandr Lobanov, Alexander Gasnikov
This paper is devoted to solving a convex stochastic optimization problem in a overparameterization setup for the case where the original gradient computation is not available, but…
Information-Theoretic Upper Bounds for Deterministic Noise in Zeroth-Order Convex Optimization
Dmitry Pasechnyuk-Vilensky, Igor Pavlov, Martin Takáč +1
We study zeroth-order convex optimization on Euclidean balls with function values corrupted by a fixed, uniformly bounded deterministic perturbation. For a query budget , the ma…
Highly Smoothness Zero-Order Methods for Solving Optimization Problems under PL Condition
Aleksandr Lobanov, Alexander Gasnikov, Fedor Stonyakin
In this paper, we study the black box optimization problem under the Polyak--Lojasiewicz (PL) condition, assuming that the objective function is not just smooth, but has higher smo…