Sparsifying Parametric Models with L0 Regularization

Nicolò Botteghi, Urban Fasel

Research output: Working paperPreprintAcademic

6 Downloads (Pure)

Abstract

This document contains an educational introduction to the problem of sparsifying parametric models with L0 regularization. We utilize this approach together with dictionary learning to learn sparse polynomial policies for deep reinforcement learning to control parametric partial differential equations. The code and a tutorial are provided here: https://github.com/nicob15/Sparsifying-Parametric-Models-with-L0.
Original languageEnglish
PublisherArXiv.org
DOIs
Publication statusPublished - 5 Sept 2024

Keywords

  • cs.LG

Fingerprint

Dive into the research topics of 'Sparsifying Parametric Models with L0 Regularization'. Together they form a unique fingerprint.

Cite this