no code implementations • ICML 2020 • Grigory Malinovsky, Dmitry Kovalev, Elnur Gasanov, Laurent Condat, Peter Richtarik
Most algorithms for solving optimization problems or finding saddle points of convex-concave functions are fixed point algorithms.
no code implementations • ICML 2020 • Zhize Li, Dmitry Kovalev, Xun Qian, Peter Richtarik
Due to the high communication cost in distributed and federated learning problems, methods relying on sparsification or quantization of communicated messages are becoming increasingly popular.
no code implementations • 29 Dec 2022 • Alexander Gasnikov, Dmitry Kovalev, Grigory Malinovsky
In this paper we study the smooth strongly convex minimization problem $\min_{x}\min_y f(x, y)$.
no code implementations • 29 Aug 2022 • Aleksandr Beznosikov, Boris Polyak, Eduard Gorbunov, Dmitry Kovalev, Alexander Gasnikov
This paper is a survey of methods for solving smooth (strongly) monotone stochastic variational inequalities.
no code implementations • 8 Jul 2022 • Abdurakhmon Sadiev, Dmitry Kovalev, Peter Richtárik
Inspired by a recent breakthrough of Mishchenko et al (2022), who for the first time showed that local gradient steps can lead to provable communication acceleration, we propose an alternative algorithm which obtains the same communication acceleration as their method (ProxSkip).
no code implementations • 16 Jun 2022 • Aleksandr Beznosikov, Aibek Alanov, Dmitry Kovalev, Martin Takáč, Alexander Gasnikov
Methods with adaptive scaling of different features play a key role in solving saddle point problems, primarily due to Adam's popularity for solving adversarial machine learning problems, including GANS training.
no code implementations • 30 May 2022 • Dmitry Kovalev, Aleksandr Beznosikov, Ekaterina Borodich, Alexander Gasnikov, Gesualdo Scutari
Finally the method is extended to distributed saddle-problems (under function similarity) by means of solving a class of variational inequalities, achieving lower communication and computation complexity bounds.
1 code implementation • 19 May 2022 • Dmitry Kovalev, Alexander Gasnikov
Arjevani et al. (2019) established the lower bound $\Omega\left(\epsilon^{-2/(3p+1)}\right)$ on the number of the $p$-th order oracle calls required by an algorithm to find an $\epsilon$-accurate solution to the problem, where the $p$-th order oracle stands for the computation of the objective function value and the derivatives up to the order $p$.
no code implementations • 11 May 2022 • Dmitry Kovalev, Alexander Gasnikov
However, the existing state-of-the-art methods do not match this lower bound: algorithms of Lin et al. (2020) and Wang and Li (2020) have gradient evaluation complexity $\mathcal{O}\left( \sqrt{\kappa_x\kappa_y}\log^3\frac{1}{\epsilon}\right)$ and $\mathcal{O}\left( \sqrt{\kappa_x\kappa_y}\log^3 (\kappa_x\kappa_y)\log\frac{1}{\epsilon}\right)$, respectively.
no code implementations • 11 Feb 2022 • Evgenia Romanenkova, Alina Rogulina, Anuar Shakirov, Nikolay Stulov, Alexey Zaytsev, Leyla Ismailova, Dmitry Kovalev, Klemens Katterbauer, Abdallah AlShehri
The essence of the interwell correlation constitutes an assessment of the similarities between geological profiles.
no code implementations • 6 Feb 2022 • Dmitry Kovalev, Aleksandr Beznosikov, Abdurakhmon Sadiev, Michael Persiianov, Peter Richtárik, Alexander Gasnikov
Our algorithms are the best among the available literature not only in the decentralized stochastic case, but also in the decentralized deterministic and non-distributed stochastic cases.
no code implementations • 30 Dec 2021 • Dmitry Kovalev, Alexander Gasnikov, Peter Richtárik
In this paper we study the convex-concave saddle-point problem $\min_x \max_y f(x) + y^T \mathbf{A} x - g(y)$, where $f(x)$ and $g(y)$ are smooth and convex functions.
no code implementations • NeurIPS 2021 • Dmitry Kovalev, Elnur Gasanov, Alexander Gasnikov, Peter Richtarik
We consider the task of minimizing the sum of smooth and strongly convex functions stored in a decentralized manner across the nodes of a communication network whose links are allowed to change in time.
no code implementations • 22 Feb 2021 • Adil Salim, Laurent Condat, Dmitry Kovalev, Peter Richtárik
Optimization problems under affine constraints appear in various areas of machine learning.
Optimization and Control
no code implementations • 18 Feb 2021 • Dmitry Kovalev, Egor Shulgin, Peter Richtárik, Alexander Rogozin, Alexander Gasnikov
We propose ADOM - an accelerated method for smooth and strongly convex decentralized optimization over time-varying networks.
1 code implementation • ICLR 2022 • Konstantin Mishchenko, Bokun Wang, Dmitry Kovalev, Peter Richtárik
We propose a family of adaptive integer compression operators for distributed Stochastic Gradient Descent (SGD) that do not communicate a single float.
no code implementations • 15 Feb 2021 • Alexander Rogozin, Alexander Beznosikov, Darina Dvinskikh, Dmitry Kovalev, Pavel Dvurechensky, Alexander Gasnikov
We consider distributed convex-concave saddle point problems over arbitrary connected undirected networks and propose a decentralized distributed algorithm for their solution.
Distributed Optimization Optimization and Control Distributed, Parallel, and Cluster Computing
no code implementations • 3 Nov 2020 • Dmitry Kovalev, Anastasia Koloskova, Martin Jaggi, Peter Richtarik, Sebastian U. Stich
Decentralized optimization methods enable on-device training of machine learning models without a central coordinator.
1 code implementation • NeurIPS 2020 • Eduard Gorbunov, Dmitry Kovalev, Dmitry Makarenko, Peter Richtárik
Moreover, using our general scheme, we develop new variants of SGD that combine variance reduction or arbitrary sampling with error feedback and quantization and derive the convergence rates for these methods beating the state-of-the-art results.
no code implementations • NeurIPS 2020 • Dmitry Kovalev, Adil Salim, Peter Richtárik
We propose two new algorithms for this decentralized optimization problem and equip them with complexity guarantees.
no code implementations • 3 Apr 2020 • Grigory Malinovsky, Dmitry Kovalev, Elnur Gasanov, Laurent Condat, Peter Richtárik
Most algorithms for solving optimization problems or finding saddle points of convex-concave functions are fixed-point algorithms.
no code implementations • 26 Feb 2020 • Zhize Li, Dmitry Kovalev, Xun Qian, Peter Richtárik
Due to the high communication cost in distributed and federated learning problems, methods relying on compression of communicated messages are becoming increasingly popular.
no code implementations • ICML 2020 • Filip Hanzely, Dmitry Kovalev, Peter Richtarik
We propose an accelerated version of stochastic variance reduced coordinate descent -- ASVRCD.
no code implementations • 20 Dec 2019 • Sélim Chraibi, Ahmed Khaled, Dmitry Kovalev, Peter Richtárik, Adil Salim, Martin Takáč
We propose basic and natural assumptions under which iterative optimization methods with compressed iterates can be analyzed.
1 code implementation • 3 Dec 2019 • Dmitry Kovalev, Konstantin Mishchenko, Peter Richtárik
We present two new remarkably simple stochastic second-order methods for minimizing the average of a very large number of sufficiently smooth and strongly convex functions.
1 code implementation • NeurIPS 2019 • Adil Salim, Dmitry Kovalev, Peter Richtárik
We propose a new algorithm---Stochastic Proximal Langevin Algorithm (SPLA)---for sampling from a log concave distribution.
no code implementations • 27 May 2019 • Konstantin Mishchenko, Dmitry Kovalev, Egor Shulgin, Peter Richtárik, Yura Malitsky
We fix a fundamental issue in the stochastic extragradient method by providing a new sampling strategy that is motivated by approximating implicit updates.
no code implementations • 24 Jan 2019 • Dmitry Kovalev, Samuel Horvath, Peter Richtarik
A key structural element in both of these methods is the inclusion of an outer loop at the beginning of which a full pass over the training data is made in order to compute the exact gradient, which is then used to construct a variance-reduced estimator of the gradient.