Searcharxiv⌕ Search

arXiv subjects

Dmitry Kamzolov

Publications and source records attributed to Dmitry Kamzolov.

32 records · Page 2Linked to original sources
arXiv2022

Hyperfast Second-Order Local Solvers for Efficient Statistically Preconditioned Distributed Optimization

Statistical preconditioning enables fast methods for distributed large-scale empirical risk minimization problems. In this approach, multiple worker nodes compute gradients in parallel, which are then used by the central node to update the parameter by solving an auxiliary (preconditioned) smaller-scale optimization problem. The recently proposed Statistically Preconditioned Accelerated Gradient (SPAG) method has complexity bounds superior to other such algorithms but requires an exact solution for computationally intensive auxiliary optimization problems at every iteration. In this paper, we propose an Inexact SPAG (InSPAG) and explicitly characterize the accuracy by which the corresponding auxiliary subproblem needs to be solved to guarantee the same convergence rate as the exact method. We build our results by first developing an inexact adaptive accelerated Bregman proximal gradient method for general optimization problems under relative smoothness and strong convexity assumptions, which may be of independent interest. Moreover, we explore the properties of the auxiliary problem in the InSPAG algorithm assuming Lipschitz third-order derivatives and strong convexity. For such problem class, we develop a linearly convergent Hyperfast second-order method and estimate the total complexity of the InSPAG method with hyperfast auxiliary problem solver. Finally, we illustrate the proposed method's practical efficiency by performing large-scale numerical experiments on logistic regression models. To the best of our knowledge, these are the first empirical results on implementing high-order methods on large-scale problems, we work with data where the dimension is of the order of~$3$ million, and the number of samples is~$700$ million.

math.OC↗
arXiv2022

Suppressing Poisoning Attacks on Federated Learning for Medical Imaging

Collaboration among multiple data-owning entities (e.g., hospitals) can accelerate the training process and yield better machine learning models due to the availability and diversity of data. However, privacy concerns make it challenging to exchange data while preserving confidentiality. Federated Learning (FL) is a promising solution that enables collaborative training through exchange of model parameters instead of raw data. However, most existing FL solutions work under the assumption that participating clients are \emph{honest} and thus can fail against poisoning attacks from malicious parties, whose goal is to deteriorate the global model performance. In this work, we propose a robust aggregation rule called Distance-based Outlier Suppression (DOS) that is resilient to byzantine failures. The proposed method computes the distance between local parameter updates of different clients and obtains an outlier score for each client using Copula-based Outlier Detection (COPOD). The resulting outlier scores are converted into normalized weights using a softmax function, and a weighted average of the local parameters is used for updating the global model. DOS aggregation can effectively suppress parameter updates from malicious clients without the need for any hyperparameter selection, even when the data distributions are heterogeneous. Evaluation on two medical imaging datasets (CheXpert and HAM10000) demonstrates the higher robustness of DOS method against a variety of poisoning attacks in comparison to other state-of-the-art methods. The code can be found here https://github.com/Naiftt/SPAFD.

cs.CR↗
arXiv2022

FLECS: A Federated Learning Second-Order Framework via Compression and Sketching

Inspired by the recent work FedNL (Safaryan et al, FedNL: Making Newton-Type Methods Applicable to Federated Learning), we propose a new communication efficient second-order framework for Federated learning, namely FLECS. The proposed method reduces the high-memory requirements of FedNL by the usage of an L-SR1 type update for the Hessian approximation which is stored on the central server. A low dimensional `sketch' of the Hessian is all that is needed by each device to generate an update, so that memory costs as well as number of Hessian-vector products for the agent are low. Biased and unbiased compressions are utilized to make communication costs also low. Convergence guarantees for FLECS are provided in both the strongly convex, and nonconvex cases, and local linear convergence is also established under strong convexity. Numerical experiments confirm the practical benefits of this new FLECS algorithm.

math.OC↗
arXiv2021

Recent Theoretical Advances in Non-Convex Optimization

Motivated by recent increased interest in optimization algorithms for non-convex optimization in application to training deep neural networks and other optimization problems in data analysis, we give an overview of recent theoretical results on global performance guarantees of optimization algorithms for non-convex optimization. We start with classical arguments showing that general non-convex problems could not be solved efficiently in a reasonable time. Then we give a list of problems that can be solved efficiently to find the global minimizer by exploiting the structure of the problem as much as it is possible. Another way to deal with non-convexity is to relax the goal from finding the global minimum to finding a stationary point or a local minimum. For this setting, we first present known results for the convergence rates of deterministic first-order methods, which are then followed by a general theoretical analysis of optimal stochastic and randomized gradient schemes, and an overview of the stochastic first-order methods. After that, we discuss quite general classes of non-convex problems, such as minimization of $α$-weakly-quasi-convex functions and functions that satisfy Polyak--Lojasiewicz condition, which still allow obtaining theoretical convergence guarantees of first-order methods. Then we consider higher-order and zeroth-order/derivative-free methods and their convergence rates for non-convex optimization problems.

math.OC↗
arXiv2021

An Accelerated Second-Order Method for Distributed Stochastic Optimization

We consider distributed stochastic optimization problems that are solved with master/workers computation architecture. Statistical arguments allow to exploit statistical similarity and approximate this problem by a finite-sum problem, for which we propose an inexact accelerated cubic-regularized Newton's method that achieves lower communication complexity bound for this setting and improves upon existing upper bound. We further exploit this algorithm to obtain convergence rate bounds for the original stochastic optimization problem and compare our bounds with the existing bounds in several regimes when the goal is to minimize the number of communication rounds and increase the parallelization by increasing the number of workers.

math.OC↗
arXiv2020

Efficient Numerical Methods to Solve Sparse Linear Equations with Application to PageRank

In this paper, we propose three methods to solve the PageRank problem for the transition matrices with both row and column sparsity. Our methods reduce the PageRank problem to the convex optimization problem over the simplex. The first algorithm is based on the gradient descent in L1 norm instead of the Euclidean one. The second algorithm extends the Frank-Wolfe to support sparse gradient updates. The third algorithm stands for the mirror descent algorithm with a randomized projection. We proof converges rates for these methods for sparse problems as well as numerical experiments support their effectiveness.

math.OC↗
arXiv2020

Accelerated meta-algorithm for convex optimization

We propose an accelerated meta-algorithm, which allows to obtain accelerated methods for convex unconstrained minimization in different settings. As an application of the general scheme we propose nearly optimal methods for minimizing smooth functions with Lipschitz derivatives of an arbitrary order, as well as for smooth minimax optimization problems. The proposed meta-algorithm is more general than the ones in the literature and allows to obtain better convergence rates and practical performance in several settings.

math.OC↗
arXiv2020

Near-Optimal Hyperfast Second-Order Method for convex optimization and its Sliding

In this paper, we present a new Hyperfast Second-Order Method with convergence rate $O(N^{-5})$ up to a logarithmic factor for the convex function with Lipshitz the third derivative. This method based on two ideas. The first comes from the superfast second-order scheme of Yu. Nesterov (CORE Discussion Paper 2020/07, 2020). It allows implementing the third-order scheme by solving subproblem using only the second-order oracle. This method converges with rate $O(N^{-4})$. The second idea comes from the work of Kamzolov et al. (arXiv:2002.01004). It is the inexact near-optimal third-order method. In this work, we improve its convergence and merge it with the scheme of solving subproblem using only the second-order oracle. As a result, we get convergence rate $O(N^{-5})$ up to a logarithmic factor. This convergence rate is near-optimal and the best known up to this moment. Further, we investigate the situation when there is a sum of two functions and improve the sliding framework from Kamzolov et al. (arXiv:2002.01004) for the second-order methods.

math.OC↗
arXiv2020

On the Optimal Combination of Tensor Optimization Methods

We consider the minimization problem of a sum of a number of functions having Lipshitz $p$-th order derivatives with different Lipschitz constants. In this case, to accelerate optimization, we propose a general framework allowing to obtain near-optimal oracle complexity for each function in the sum separately, meaning, in particular, that the oracle for a function with lower Lipschitz constant is called a smaller number of times. As a building block, we extend the current theory of tensor methods and show how to generalize near-optimal tensor methods to work with inexact tensor step. Further, we investigate the situation when the functions in the sum have Lipschitz derivatives of a different order. For this situation, we propose a generic way to separate the oracle complexity between the parts of the sum. Our method is not optimal, which leads to an open problem of the optimal combination of oracles of a different order.

math.OC↗
arXiv2019

Universal Intermediate Gradient Method for Convex Problems with Inexact Oracle

In this paper, we propose new first-order methods for minimization of a convex function on a simple convex set. We assume that the objective function is a composite function given as a sum of a simple convex function and a convex function with inexact Hölder-continuous subgradient. We propose Universal Intermediate Gradient Method. Our method enjoys both the universality and intermediateness properties. Following the paper by Y. Nesterov (Math.Prog., 2015) on Universal Gradient Methods, our method does not require any information about the Hölder parameter and constant and adjusts itself automatically to the local level of smoothness. On the other hand, in the spirit of the preprint by O. Devolder, F.Glineur, and Y. Nesterov (CORE DP 2013/17), our method is intermediate in the sense that it interpolates between Universal Gradient Method and Universal Fast Gradient Method. This allows to balance the rate of convergence of the method and rate of the oracle error accumulation. Under additional assumption of strong convexity of the objective, we show how the restart technique can be used to obtain an algorithm with faster rate of convergence.

math.OC↗
arXiv2019

Composite optimization for the resource allocation problem

In this paper we consider resource allocation problem stated as a convex minimization problem with linear constraints. To solve this problem, we use gradient and accelerated gradient descent applied to the dual problem and prove the convergence rate both for the primal iterates and the dual iterates. We obtain faster convergence rates than the ones known in the literature. We also provide economic interpretation for these two methods. This means that iterations of the algorithms naturally correspond to the process of price and production adjustment in order to obtain the desired production volume in the economy. Overall, we show how these actions of the economic agents lead the whole system to the equilibrium.

math.OC↗
arXiv2016

Universal method with inexact oracle and its applications for searching equillibriums in multistage transport problems

In this paper we propose a new efficient approach for numerical calculation of equillibriums in multistage transport problems. In the very core of our approach lies the proper combination of Universal Gradient Method proposed by Yu. Nesterov (2013) and conception of inexact oracle (Devolder--Glineur--Nesterov, 2011). In particular our technique allows us to calculate Wasserstein's Barycenter in a fast manner (this results generalized M. Cuturi et al. (2014)).

math.OC↗
arXiv2016

Gradient and gradient-free methods for stochastic convex optimization with inexact oracle

In the paper we generalize universal gradient method (Yu. Nesterov) to strongly convex case and to Intermediate gradient method (Devolder-Glineur-Nesterov). We also consider possible generalizations to stochastic and online context. We show how these results can be generalized to gradient-free method and method of random direction search. But the main ingridient of this paper is assumption about the oracle. We considered the oracle to be inexact.

math.OC↗