Search Results for author: Pontus Giselsson

Found 8 papers, 5 papers with code

Sampling and Update Frequencies in Proximal Variance-Reduced Stochastic Gradient Methods

no code implementations13 Feb 2020 Martin Morin, Pontus Giselsson

Variance-reduced stochastic gradient methods have gained popularity in recent times.

Two Applications of Deep Learning in the Physical Layer of Communication Systems

no code implementations10 Jan 2020 Emil Björnson, Pontus Giselsson

Deep learning has proved itself to be a powerful tool to develop data-driven signal processing algorithms for challenging engineering problems.

Decision Making

Cocoercivity, Smoothness and Bias in Variance-Reduced Stochastic Gradient Methods

no code implementations21 Mar 2019 Martin Morin, Pontus Giselsson

However, in the biased cases they still do not correspond well with practical experiences and we therefore examine the effect of bias numerically on a set of classification problems.

Operator Splitting Performance Estimation: Tight contraction factors and optimal parameter selection

1 code implementation1 Dec 2018 Ernest K. Ryu, Adrien B. Taylor, Carolina Bergeling, Pontus Giselsson

We propose a methodology for studying the performance of common splitting methods through semidefinite programming.

Optimization and Control 47H05 47H09 68Q25 90C22 90C25 90C30 90C60

Efficient Proximal Mapping Computation for Unitarily Invariant Low-Rank Inducing Norms

2 code implementations17 Oct 2018 Christian Grussler, Pontus Giselsson

This is known for the nuclear norm, but not for most other members of the low-rank inducing family.

Local Convergence of Proximal Splitting Methods for Rank Constrained Problems

2 code implementations11 Oct 2017 Christian Grussler, Pontus Giselsson

We analyze the local convergence of proximal splitting algorithms to solve optimization problems that are convex besides a rank constraint.

Low-Rank Inducing Norms with Optimality Interpretations

2 code implementations9 Dec 2016 Christian Grussler, Pontus Giselsson

A posteriori guarantees on solving an underlying rank constrained optimization problem with these convex relaxations are provided.

Matrix Completion

Low-rank Optimization with Convex Constraints

1 code implementation6 Jun 2016 Christian Grussler, Anders Rantzer, Pontus Giselsson

In this paper, we propose an alternative convex relaxation that uses the convex envelope of the squared Frobenius norm and the rank constraint.

Cannot find the paper you are looking for? You can Submit a new open access paper.