Maestro: Uncovering Low-Rank Structures via Trainable Decomposition

Samuel Horváth; Stefanos Laskaridis; Shashank Rajput; Hongyi Wang

2024 ICML ICML 2024

Maestro: Uncovering Low-Rank Structures via Trainable Decomposition

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Samuel Horváth, Stefanos Laskaridis, Shashank Rajput, Hongyi Wang

Topics

Machine Learning > Application Areas > Efficient Computing Deep Learning > Architectures > Neural Networks Deep Learning > Learning Types > Representation Learning

Keywords

low rank compression importance ordering layer granularity lod trainable decomposition

Download PDF