L$_0$onie: Compressing COINs with L$_0$-constraints

Author name not available (Why is that?)

Publication date: 8 July 2022

Abstract: Advances in Implicit Neural Representations (INR) have motivated research on domain-agnostic compression techniques. These methods train a neural network to approximate an object, and then store the weights of the trained model. For example, given an image, a network is trained to learn the mapping from pixel locations to RGB values. In this paper, we propose L

_{0}

onie, a sparsity-constrained extension of the COIN compression method. Sparsity allows to leverage the faster learning of overparameterized networks, while retaining the desirable compression rate of smaller models. Moreover, our constrained formulation ensures that the final model respects a pre-determined compression rate, dispensing of the need for expensive architecture search.

Has companion code repository: https://github.com/juan43ramirez/l0onie

This page was built for publication: L$_0$onie: Compressing COINs with L$_0$-constraints

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6404453)