papers

Publications (22)

cs.LG2022

Personalized Federated Learning with Multiple Known Clusters

Boxiang Lyu, Filip Hanzely, Mladen Kolar

We consider the problem of personalized federated learning when there are known cluster structures within users. An intuitive approach would be to regularize the parameters so that…

math.OC2020

Stochastic Subspace Cubic Newton Method

Filip Hanzely, Nikita Doikov, Peter Richtárik +1

In this paper, we propose a new randomized second-order optimization algorithm---Stochastic Subspace Cubic Newton (SSCN)---for minimizing a high dimensional convex function . Ou…

math.OC2017

Privacy Preserving Randomized Gossip Algorithms

Filip Hanzely, Jakub Konečný, Nicolas Loizou +2

In this work we present three different randomized gossip algorithms for solving the average consensus problem while at the same time protecting the information about the initial p…

math.OC2020

Optimization for Supervised Machine Learning: Randomized Algorithms for Data and Parameters

Filip Hanzely

Many key problems in machine learning and data science are routinely modeled as optimization problems and solved via optimization algorithms. With the increase of the volume of dat…

math.OC2019

A Unified Theory of SGD: Variance Reduction, Sampling, Quantization and Coordinate Descent

Eduard Gorbunov, Filip Hanzely, Peter Richtárik

In this paper we introduce a unified analysis of a large family of variants of proximal stochastic gradient descent ({\tt SGD}) which so far have required different intuitions, con…

cs.LG2021

Federated Learning of a Mixture of Global and Local Models

Filip Hanzely, Peter Richtárik

We propose a new optimization formulation for training federated learning models. The standard formulation has the form of an empirical risk minimization problem constructed to fin…

math.OC2018

Fastest Rates for Stochastic Mirror Descent Methods

Filip Hanzely, Peter Richtárik

Relative smoothness - a notion introduced by Birnbaum et al. (2011) and rediscovered by Bauschke et al. (2016) and Lu et al. (2016) - generalizes the standard notion of smoothness…

cs.LG2021

A Field Guide to Federated Optimization

Jianyu Wang, Zachary Charles, Zheng Xu +50

Federated learning and analytics are a distributed approach for collaboratively learning models (or statistics) from decentralized data, motivated by and designed for privacy prote…

math.OC2020

Variance Reduced Coordinate Descent with Acceleration: New Method With a Surprising Application to Finite-Sum Problems

Filip Hanzely, Dmitry Kovalev, Peter Richtarik

We propose an accelerated version of stochastic variance reduced coordinate descent -- ASVRCD. As other variance reduced coordinate descent methods such as SEGA or SVRCD, our metho…

math.OC2018

SEGA: Variance Reduction via Gradient Sketching

Filip Hanzely, Konstantin Mishchenko, Peter Richtarik

We propose a randomized first order optimization method--SEGA (SkEtched GrAdient method)-- which progressively throughout its iterations builds a variance-reduced estimate of the g…

math.OC2019

Best Pair Formulation & Accelerated Scheme for Non-convex Principal Component Pursuit

Aritra Dutta, Filip Hanzely, Jingwei Liang +1

The best pair problem aims to find a pair of points that minimize the distance between two disjoint sets. In this paper, we formulate the classical robust principal component analy…

cs.LG2021

Smoothness Matrices Beat Smoothness Constants: Better Communication Compression Techniques for Distributed Optimization

Mher Safaryan, Filip Hanzely, Peter Richtárik

Large scale distributed optimization has become the default tool for the training of supervised machine learning models with a large number of parameters and training data. Recent…

math.OC2019

A Privacy Preserving Randomized Gossip Algorithm via Controlled Noise Insertion

Filip Hanzely, Jakub Konečný, Nicolas Loizou +2

In this work we present a randomized gossip algorithm for solving the average consensus problem while at the same time protecting the information about the initial private values s…

math.OC2018

Accelerated Coordinate Descent with Arbitrary Sampling and Best Rates for Minibatches

Filip Hanzely, Peter Richtárik

Accelerated coordinate descent is a widely popular optimization algorithm due to its efficiency on large-dimensional problems. It achieves state-of-the-art complexity on an importa…

cs.LG2023

Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques

Filip Hanzely, Boxin Zhao, Mladen Kolar

We investigate the optimization aspects of personalized Federated Learning (FL). We propose general optimizers that can be applied to numerous existing personalized FL objectives,…

cs.LG2020

Lower Bounds and Optimal Algorithms for Personalized Federated Learning

Filip Hanzely, Slavomír Hanzely, Samuel Horváth +1

In this work, we consider the optimization formulation of personalized federated learning recently introduced by Hanzely and Richtárik (2020) which was shown to give an alternativ…

math.OC2020

One Method to Rule Them All: Variance Reduction for Data, Parameters and Many New Methods

Filip Hanzely, Peter Richtárik

We propose a remarkably general variance-reduced method suitable for solving regularized empirical risk minimization problems with either a large number of training examples, or a…

math.OC2020

A Nonconvex Projection Method for Robust PCA

Aritra Dutta, Filip Hanzely, Peter Richtárik

Robust principal component analysis (RPCA) is a well-studied problem with the goal of decomposing a matrix into the sum of low-rank and sparse components. In this paper, we propose…

math.OC2018

Accelerated Stochastic Matrix Inversion: General Theory and Speeding up BFGS Rules for Faster Second-Order Optimization

Robert M. Gower, Filip Hanzely, Peter Richtárik +1

We present the first accelerated randomized algorithm for solving linear systems in Euclidean spaces. One essential problem of this type is the matrix inversion problem. In particu…

cs.LG2020

Local SGD: Unified Theory and New Efficient Methods

Eduard Gorbunov, Filip Hanzely, Peter Richtárik

We present a unified framework for analyzing local SGD methods in the convex and strongly convex regimes for distributed/federated training of supervised machine learning models. W…

cs.LG2019

99% of Distributed Optimization is a Waste of Time: The Issue and How to Fix it

Konstantin Mishchenko, Filip Hanzely, Peter Richtárik

Many popular distributed optimization methods for training machine learning models fit the following template: a local gradient estimate is computed independently by each worker, t…

math.OC2021

Accelerated Bregman Proximal Gradient Methods for Relatively Smooth Convex Optimization

Filip Hanzely, Peter Richtarik, Lin Xiao

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, and the other can be…