Sparsifying Parametric Models with L0 Regularization
This is an incremental approach for researchers in machine learning and computational science, focusing on model sparsity in specific applications.
The paper tackles the problem of sparsifying parametric models using L0 regularization, applying it with dictionary learning to learn sparse polynomial policies for deep reinforcement learning in controlling parametric partial differential equations, with code and a tutorial provided.
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.