no code implementations • 6 Feb 2024 • Emanuele Zangrando, Piero Deidda, Simone Brugiapaglia, Nicola Guglielmi, Francesco Tudisco
Recent work in deep learning has shown strong empirical and theoretical evidence of an implicit low-rank bias: weight matrices in deep networks tend to be approximately low-rank and removing relatively small singular values during training or from available trained models may significantly reduce model size while maintaining or even improving model performance.
no code implementations • 30 May 2023 • Emanuele Zangrando, Steffen Schotthöfer, Gianluca Ceruti, Jonas Kusch, Francesco Tudisco
The computing cost and memory demand of deep learning pipelines have grown fast in recent years and thus a variety of pruning techniques have been developed to reduce model parameters.
4 code implementations • 26 May 2022 • Steffen Schotthöfer, Emanuele Zangrando, Jonas Kusch, Gianluca Ceruti, Francesco Tudisco
The main idea is to restrict the weight matrices to a low-rank manifold and to update the low-rank factors rather than the full matrix during training.