Stochastic optimization with heavy-tailed noise via accelerated gradient clipping
E Gorbunov, M Danilova… - Advances in Neural …, 2020 - proceedings.neurips.cc
In this paper, we propose a new accelerated stochastic first-order method called clipped-
SSTM for smooth convex stochastic optimization with heavy-tailed distributed noise in …
SSTM for smooth convex stochastic optimization with heavy-tailed distributed noise in …
Universal method for stochastic composite optimization problems
AV Gasnikov, YE Nesterov - Computational Mathematics and …, 2018 - Springer
A fast gradient method requiring only one projection is proposed for smooth convex
optimization problems. The method has a visual geometric interpretation, so it is called the …
optimization problems. The method has a visual geometric interpretation, so it is called the …
Randomized gradient-free methods in convex optimization
Consider a convex optimization problem min x∈ Q⊆ Rd f (x)(1) with convex feasible set Q
and convex objective f possessing the zeroth-order (gradient/derivativefree) oracle [83]. The …
and convex objective f possessing the zeroth-order (gradient/derivativefree) oracle [83]. The …
Accelerated methods for saddle-point problem
Recently, it has been shown how, on the basis of the usual accelerated gradient method for
solving problems of smooth convex optimization, accelerated methods for more complex …
solving problems of smooth convex optimization, accelerated methods for more complex …
Stochastic online optimization. Single-point and multi-point non-linear multi-armed bandits. Convex and strongly-convex case
AV Gasnikov, EA Krymova, AA Lagunovskaya… - Automation and remote …, 2017 - Springer
In this paper the gradient-free modification of the mirror descent method for convex
stochastic online optimization problems is proposed. The crucial assumption in the problem …
stochastic online optimization problems is proposed. The crucial assumption in the problem …
On accelerated methods for saddle-point problems with composite structure
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 …
bilinear objective and different condition numbers with respect to the primal and the dual …
Universal gradient descent
A Gasnikov - arXiv preprint arXiv:1711.00394, 2017 - arxiv.org
In this book we collect many different and useful facts around gradient descent method. First
of all we consider gradient descent with inexact oracle. We build a general model of …
of all we consider gradient descent with inexact oracle. We build a general model of …
[PDF][PDF] Randomized similar triangles method: A unifying framework for accelerated randomized optimization methods (coordinate descent, directional search …
P Dvurechensky, A Gasnikov… - arXiv preprint arXiv …, 2017 - optimization-online.org
In this paper, we consider smooth convex optimization problems with simple constraints and
inexactness in the oracle information such as value, partial or directional derivatives of the …
inexactness in the oracle information such as value, partial or directional derivatives of the …
Dual approaches to the minimization of strongly convex functionals with a simple structure under affine constraints
AS Anikin, AV Gasnikov, PE Dvurechensky… - Computational …, 2017 - Springer
A strongly convex function of simple structure (for example, separable) is minimized under
affine constraints. A dual problem is constructed and solved by applying a fast gradient …
affine constraints. A dual problem is constructed and solved by applying a fast gradient …
Efficient numerical methods for entropy-linear programming problems
AV Gasnikov, EB Gasnikova, YE Nesterov… - Computational …, 2016 - Springer
Entropy-linear programming (ELP) problems arise in various applications. They are usually
written as the maximization of entropy (minimization of minus entropy) under affine …
written as the maximization of entropy (minimization of minus entropy) under affine …