1 code implementation • 11 Oct 2023 • Aaron Defazio, Ashok Cutkosky, Harsh Mehta, Konstantin Mishchenko
To go beyond this worst-case analysis, we use the observed gradient norms to derive schedules refined for any particular task.
1 code implementation • 4 Aug 2023 • Yura Malitsky, Konstantin Mishchenko
In this paper, we explore two fundamental first-order algorithms in convex optimization, namely, gradient descent (GD) and proximal gradient method (ProxGD).
1 code implementation • 9 Jun 2023 • Konstantin Mishchenko, Aaron Defazio
We consider the problem of estimating the learning rate in adaptive methods, such as AdaGrad and Adam.
no code implementations • 29 May 2023 • Konstantin Mishchenko, Rustem Islamov, Eduard Gorbunov, Samuel Horváth
We present a partially personalized formulation of Federated Learning (FL) that strikes a balance between the flexibility of personalization and cooperativeness of global training.
1 code implementation • NeurIPS 2023 • Ahmed Khaled, Konstantin Mishchenko, Chi Jin
This paper proposes a new easy-to-implement parameter-free gradient-based optimizer: DoWG (Distance over Weighted Gradients).
no code implementations • 7 Feb 2023 • Blake Woodworth, Konstantin Mishchenko, Francis Bach
We present an algorithm for minimizing an objective with hard-to-compute gradients by using a related, easier-to-access function as a proxy.
1 code implementation • 18 Jan 2023 • Aaron Defazio, Konstantin Mishchenko
D-Adaptation is an approach to automatically setting the learning rate which asymptotically achieves the optimal rate of convergence for minimizing convex Lipschitz functions, with no back-tracking or line searches, and no additional function value or gradient evaluations per step.
no code implementations • 17 Jan 2023 • Konstantin Mishchenko, Slavomír Hanzely, Peter Richtárik
As a special case, our theory allows us to show the convergence of First-Order Model-Agnostic Meta-Learning (FO-MAML) to the vicinity of a solution of Moreau objective.
no code implementations • 11 Aug 2022 • Nikita Doikov, Konstantin Mishchenko, Yurii Nesterov
We analyze the performance of a variant of Newton method with quadratic regularization for solving composite convex minimization problems.
no code implementations • 10 Aug 2022 • Samuel Horváth, Konstantin Mishchenko, Peter Richtárik
In this work, we propose new adaptive step size strategies that improve several stochastic gradient methods.
1 code implementation • 15 Jun 2022 • Konstantin Mishchenko, Francis Bach, Mathieu Even, Blake Woodworth
The existing analysis of asynchronous stochastic gradient descent (SGD) degrades dramatically when any delay is large, giving the impression that performance depends primarily on the delay.
no code implementations • 18 Feb 2022 • Konstantin Mishchenko, Grigory Malinovsky, Sebastian Stich, Peter Richtárik
The canonical approach to solving such problems is via the proximal gradient descent (ProxGD) algorithm, which is based on the evaluation of the gradient of $f$ and the prox operator of $\psi$ in each iteration.
no code implementations • 26 Jan 2022 • Grigory Malinovsky, Konstantin Mishchenko, Peter Richtárik
Together, our results on the advantage of large and small server-side stepsizes give a formal justification for the practice of adaptive server-side optimization in federated learning.
2 code implementations • 3 Dec 2021 • Konstantin Mishchenko
We present a Newton-type method that converges fast from any initialization and for arbitrary convex objectives with Lipschitz Hessians.
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.
1 code implementation • NeurIPS 2021 • Konstantin Mishchenko, Ahmed Khaled, Peter Richtárik
Random Reshuffling (RR), also known as Stochastic Gradient Descent (SGD) without replacement, is a popular and theoretically grounded method for finite-sum minimization.
1 code implementation • NeurIPS 2020 • Konstantin Mishchenko, Ahmed Khaled, Peter Richtárik
from $\kappa$ to $\sqrt{\kappa}$) and, in addition, show that RR has a different type of variance.
no code implementations • 3 Apr 2020 • Adil Salim, Laurent Condat, Konstantin Mishchenko, Peter Richtárik
We consider minimizing the sum of three convex functions, where the first one F is smooth, the second one is nonsmooth and proximable and the third one is the composition of a nonsmooth proximable function with a linear operator L. This template problem has many applications, for instance, in image processing and machine learning.
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 • ICML 2020 • Yura Malitsky, Konstantin Mishchenko
We present a strikingly simple proof that two rules are sufficient to automate gradient descent: 1) don't increase the stepsize too fast and 2) don't overstep the local curvature.
no code implementations • 16 Sep 2019 • Konstantin Mishchenko
We present a new perspective on the celebrated Sinkhorn algorithm by showing that is a special case of incremental/stochastic mirror descent.
no code implementations • 10 Sep 2019 • Ahmed Khaled, Konstantin Mishchenko, Peter Richtárik
We provide a new analysis of local SGD, removing unnecessary assumptions and elaborating on the difference between two data regimes: identical and heterogeneous.
no code implementations • 10 Sep 2019 • Ahmed Khaled, Konstantin Mishchenko, Peter Richtárik
We provide the first convergence analysis of local gradient descent for minimizing the average of smooth and convex but otherwise arbitrary functions.
no code implementations • 25 Jun 2019 • Konstantin Mishchenko, Mallory Montgomery, Federico Vaggi
When forecasting time series with a hierarchical structure, the existing state of the art is to forecast each time series independently, and, in a post-treatment step, to reconcile the time series in a way that respects the hierarchy (Hyndman et al., 2011; Wickramasuriya et al., 2018).
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 • 27 Jan 2019 • Konstantin Mishchenko, Filip Hanzely, Peter Richtárik
We propose a fix based on a new update-sparsification method we develop in this work, which we suggest be used on top of existing methods.
no code implementations • 26 Jan 2019 • Konstantin Mishchenko, Eduard Gorbunov, Martin Takáč, Peter Richtárik
Our analysis of block-quantization and differences between $\ell_2$ and $\ell_{\infty}$ quantization closes the gaps in theory and practice.
no code implementations • NeurIPS 2018 • Filip Hanzely, Konstantin Mishchenko, Peter Richtarik
In each iteration, SEGA updates the current estimate of the gradient through a sketch-and-project operation using the information provided by the latest sketch, and this is subsequently used to compute an unbiased estimate of the true gradient through a random relaxation procedure.
no code implementations • ICML 2018 • Konstantin Mishchenko, Franck Iutzeler, Jérôme Malick, Massih-Reza Amini
One of the main challenges is then to deal with heterogeneous machines and unreliable communications.
no code implementations • 25 Jun 2018 • Konstantin Mishchenko, Franck Iutzeler, Jérôme Malick
We develop and analyze an asynchronous algorithm for distributed convex optimization when the objective writes a sum of smooth functions, local to each worker, and a non-smooth function.