Topologies on spaces of linear maps

Publications associées (29)

À propos
Confidentialité
Mentions légales

Graph Chatbot

Dictionary Learning for Two-Dimensional Kendall Shapes

Michaël Unser, Julien René Pierre Fageot, Virginie Sophie Uhlmann, Anna You-Lai Song

We propose a novel sparse dictionary learning method for planar shapes in the sense of Kendall, namely configurations of landmarks in the plane considered up to similitudes. Our shape dictionary method provides a good trade-off between algorithmic simplici ...

SIAM PUBLICATIONS2020

Quenched convergence and strong local equilibrium for asymmetric zero-range process with site disorder

Thomas Mountford

We study asymmetric zero-range processes on Z with nearest-neighbour jumps and site disorder. The jump rate of particles is an arbitrary but bounded nondecreasing function of the number of particles. We prove quenched strong local equilibrium at subcritica ...

SPRINGER HEIDELBERG2020

A Linearly Convergent Algorithm for Decentralized Optimization: Sending Less Bits for Free!

Martin Jaggi, Anastasiia Koloskova

Decentralized optimization methods enable on-device training of machine learning models without a central coordinator. In many scenarios communication between devices is energy demanding and time consuming and forms the bottleneck of the entire system. We ...

MICROTOME PUBLISHING2020

On the convergence of stochastic primal-dual hybrid gradient

Volkan Cevher, Ahmet Alacaoglu

In this paper, we analyze the recently proposed stochastic primal-dual hybrid gradient (SPDHG) algorithm and provide new theoretical results. In particular, we prove almost sure convergence of the iterates to a solution and linear convergence with standard ...

2019

A Linearly Convergent Proximal Gradient Algorithm for Decentralized Optimization

Ali H. Sayed, Kun Yuan, Sulaiman A S A E Alghunaim

Decentralized optimization is a powerful paradigm that finds applications in engineering and learning design. This work studies decentralized composite optimization problems with non-smooth regularization terms. Most existing gradient-based proximal decent ...

NEURAL INFORMATION PROCESSING SYSTEMS (NIPS)2019

Convergence Of Variance-Reduced Learning Under Random Reshuffling

Ali H. Sayed, Bicheng Ying, Kun Yuan

Several useful variance-reduced stochastic gradient algorithms, such as SVRG, SAGA, Finito, and SAG, have been proposed to minimize empirical risks with linear convergence properties to the exact minimizers. The existing convergence results assume uniform ...

IEEE2018

On Matching Pursuit and Coordinate Descent

Martin Jaggi, Sebastian Urban Stich, Sai Praneeth Reddy Karimireddy, Anant Raj

Two popular examples of first-order optimization methods over linear spaces are coordinate descent and matching pursuit algorithms, with their randomized variants. While the former targets the optimization by moving along coordinates, the latter considers ...

2018

On the linear convergence of the stochastic gradient method with constant step-size

Volkan Cevher, Cong Bang Vu

The strong growth condition (SGC) is known to be a sufficient condition for linear convergence of the stochastic gradient method using a constant step-size γ (SGM-CS). In this paper, we provide a necessary condition, for the linear convergence of SGM-CS, t ...

2018

Non-convex, non-local functionals converging to the total variation

Hoài-Minh Nguyên

We present new results concerning the approximation of the total variation, integral(Omega)vertical bar del u vertical bar, of a function u by non-local, non-convex functionals of the form Lambda delta(u) = integral(Omega)integral(Omega)delta phi(vertical ...

Elsevier2017

Hypomonotonicity of the Normal Cone and Proximal Smoothness

Grigory Ivanov

We study the properties of the normal cone to a proximally smooth set. We give a complete characterization of a proximally smooth set through the monotonicity properties of its normal cone in an arbitrary uniformly convex and uniformly smooth Banach space. ...

Heldermann Verlag2017

Page 2 sur 3