Search Results - "Richtárik, Peter"

Momentum and stochastic momentum for stochastic gradient, Newton, proximal point and subspace descent methods by Loizou, Nicolas, Richtárik, Peter

“…In this paper we study several classes of stochastic optimization algorithms enriched with heavy ball momentum . Among the methods studied are: stochastic…”
Get full text

Iteration complexity of randomized block-coordinate descent methods for minimizing a composite function by Richtarik, Peter, Takac, Martin

“…In this paper we develop a randomized block-coordinate descent method for minimizing the sum of a smooth and a simple nonsmooth block-separable convex function…”
Get full text

Revisiting Randomized Gossip Algorithms: General Framework, Convergence Rates and Novel Block and Accelerated Protocols by Loizou, Nicolas, Richtarik, Peter

“…In this work we present a new framework for the analysis and design of randomized gossip algorithms for solving the average consensus problem. We show how…”
Get full text

Coordinate descent with arbitrary sampling I: algorithms and complexity by Qu, Zheng, Richtárik, Peter

“…We study the problem of minimizing the sum of a smooth convex function and a convex block-separable regularizer and propose a new randomized coordinate descent…”
Get full text

Parallel coordinate descent methods for big data optimization by Richtarik, Peter, TakaAe, Martin

“…In this work we show that randomized (block) coordinate descent methods can be accelerated by parallelization when applied to the problem of minimizing the sum…”
Get full text

A Randomized Exchange Algorithm for Computing Optimal Approximate Designs of Experiments by Harman, Radoslav, Filová, Lenka, Richtárik, Peter

“…We propose a class of subspace ascent methods for computing optimal approximate designs that covers existing algorithms as well as new and more efficient ones…”
Get full text

Variance-Reduced Methods for Machine Learning by Gower, Robert M., Schmidt, Mark, Bach, Francis, Richtarik, Peter

“…Stochastic optimization lies at the heart of machine learning, and its cornerstone is stochastic gradient descent ( SGD ), a method introduced over 60 years…”
Get full text

Coordinate descent with arbitrary sampling II: expected separable overapproximation by Qu, Zheng, Richtárik, Peter

“…The design and complexity analysis of randomized coordinate descent methods, and in particular of variants which update a random subset (sampling) of…”
Get full text

Dualize, Split, Randomize: Toward Fast Nonsmooth Optimization Algorithms by Salim, Adil, Condat, Laurent, Mishchenko, Konstantin, Richtárik, Peter

“…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…”
Get full text

Randomized Distributed Mean Estimation: Accuracy vs. Communication by Konečný, Jakub, Richtárik, Peter

“…We consider the problem of estimating the arithmetic average of a finite collection of real vectors stored in a distributed fashion across several compute…”
Get full text

Fastest rates for stochastic mirror descent methods by Hanzely, Filip, Richtárik, Peter

“…Relative smoothness—a notion introduced in Birnbaum et al. (Proceedings of the 12th ACM conference on electronic commerce, ACM, pp 127–136, 2011) and recently…”
Get full text

Stochastic quasi-gradient methods: variance reduction via Jacobian sketching by Gower, Robert M., Richtárik, Peter, Bach, Francis

“…We develop a new family of variance reduced stochastic gradient descent methods for minimizing the average of a very large number of smooth functions. Our…”
Get full text

On optimal probabilities in stochastic coordinate descent methods by Richtárik, Peter, Takáč, Martin

“…We propose and analyze a new parallel coordinate descent method—NSync—in which at each iteration a random subset of coordinates is updated, in parallel,…”
Get full text

Inexact Coordinate Descent: Complexity and Preconditioning by Tappenden, Rachael, Richtárik, Peter, Gondzio, Jacek

“…One of the key steps at each iteration of a randomized block coordinate descent method consists in determining the update to a block of variables. Existing…”
Get full text

Optimization in High Dimensions via Accelerated, Parallel, and Proximal Coordinate Descent by Fercoq, Olivier, Richtárik, Peter

“…We propose a new randomized coordinate descent method for minimizing the sum of convex functions, each of which depends on a small number of coordinates only…”
Get full text

Stochastic distributed learning with gradient quantization and double-variance reduction by Horváth, Samuel, Kovalev, Dmitry, Mishchenko, Konstantin, Richtárik, Peter, Stich, Sebastian

“…We consider distributed optimization over several devices, each sending incremental model updates to a central server. This setting is considered, for…”
Get full text

Best Pair Formulation & Accelerated Scheme for Non-Convex Principal Component Pursuit by Dutta, Aritra, Hanzely, Filip, Liang, Jingwei, Richtarik, Peter

“…Given two disjoint sets, the best pair problem aims to find a point in one set and another point in the other set with minimal distance between them. In this…”
Get full text

Unified Analysis of Stochastic Gradient Methods for Composite Convex and Smooth Optimization by Khaled, Ahmed, Sebbouh, Othmane, Loizou, Nicolas, Gower, Robert M., Richtárik, Peter

“…We present a unified theorem for the convergence analysis of stochastic gradient algorithms for minimizing a smooth and convex loss plus a convex regularizer…”
Get full text

Semi-Stochastic Gradient Descent Methods by Konečný, Jakub, Richtárik, Peter

“…In this paper we study the problem of minimizing the average of a large number of smooth convex loss functions. We propose a new method, S2GD (Semi-Stochastic…”
Get full text

Accelerated Bregman proximal gradient methods for relatively smooth convex optimization by Hanzely, Filip, Richtárik, Peter, Xiao, Lin

“…We consider the problem of minimizing the sum of two convex functions: one is differentiable and relatively smooth with respect to a reference convex function,…”
Get full text