https://github.com/selimchraibi/distributed-bregman

https://github.com/selimchraibi/distributed-bregman

Last synced: 13 days ago
JSON representation

• Host: GitHub
• URL: https://github.com/selimchraibi/distributed-bregman
• Owner: SelimChraibi
• Created: 2022-09-13T18:19:41.000Z (about 2 years ago)
• Default Branch: master
• Last Pushed: 2023-01-16T12:47:14.000Z (almost 2 years ago)
• Last Synced: 2023-10-05T06:49:46.410Z (about 1 year ago)
• Language: Jupyter Notebook
• Size: 15.5 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Distributed Delay-Tolerant Bregman Descent

This repo implements a distributed and asynchronous optimisation algorithm. This algorithm is an adaptation of the non-distributed Bregman descent algorithm [^1].

The convergence properties of this algorithm are described in our paper [^2].

To start using the code, `cd` to the project directory, then switch to julia's REPL mode and call

```shell

(v1.0) pkg> activate .

(DistributedBregman) pkg> instantiate

```

To reploduce the plots seen in the paper, switch to a command line and run

```shell

$ julia main_fig.jl 

```

[^1]: Bolte, Jérôme & Bauschke, Heinz & Teboulle, Marc. (2016). A Descent Lemma Beyond Lipschitz Gradient Continuity: First-Order Methods Revisited and Applications. Mathematics of Operations Research. 42. 10.1287/moor.2016.0817. 

[^2]: S. Chraibi, F. Iutzelera, J. Malick and A. Rogozin. (2022). Delay-tolerant Distributed Bregman Proximal Algorithms.