View Uppdrag

Uppdrag

Rubrik

Organisation/Företag

Plats

Uppdrag

Beskrivning

Background: The technological advancement of the past decade have led to a widespread deployment of multi-agent systems in a broad range of applications, including healthcare, Internet-of-Things, robotics, power grids, and traffic networks. These systems are composed of agents equipped with computational resources and connected through a network. This decentralized architecture enables the cooperative solution of learning problems without the need to share private data. However, there is a growing concern regarding the sustainability of the decentralized learning paradigm. Thus it is important to 1) design sustainable decentralized learning techniques, and 2) thoroughly assess their footprint, and compare it with traditional, centralized learning.

Objective: The project focuses on the development of sustainable decentralized learning algorithms, and the assessment of their footprint. The roadmap of the project is as follows: 1) guided literature review, 2) design of sustainable algorithms, 3) sustainability assessment and comparison with traditional techniques, 4) numerical evaluations. The project has the potential to lead to conference and journal publications in top venues.

We are looking for 1 student to join this project. Requirements are: some programming skills (Python), and optionally background on optimization and machine learning.

The start date is flexible, and the project will take around 20 weeks.

The project will be conducted in the Division of Decision and Control Systems, with flexible remote work, under the supervision of Dr. Nicola Bastianello (nicolba@kth.se).

Det finns inga poster att visa.

Du har inte behörighet att visa de här posterna.

Fel när begäran slutfördes.

Läser in ...

Sista ansökningsdatum

Publiceringsdatum

Omfattning

Applikationskanal

E-post för ansökan

Appens URL

Ansökningshandlingar

CV, academic transcripts, motivation letter (optional)