no code implementations • 11 Dec 2023 • Paniz Halvachi, Alexandra Peste, Dan Alistarh, Christoph H. Lampert
We present ELSA, a practical solution for creating deep networks that can easily be deployed at different levels of sparsity.
no code implementations • 3 Aug 2023 • Denis Kuznedelev, Eldar Kurtic, Eugenia Iofinova, Elias Frantar, Alexandra Peste, Dan Alistarh
Obtaining versions of deep neural networks that are both highly-accurate and highly-sparse is one of the main challenges in the area of model compression, and several high-performance pruning techniques have been investigated by the community.
1 code implementation • NeurIPS 2023 • Mher Safaryan, Alexandra Peste, Dan Alistarh
We show that, in the context of linear and deep linear models, KD can be interpreted as a novel type of stochastic variance reduction mechanism.
no code implementations • CVPR 2023 • Eugenia Iofinova, Alexandra Peste, Dan Alistarh
Pruning - that is, setting a significant subset of the parameters of a neural network to zero - is one of the most popular methods of model compression.
1 code implementation • 28 Jul 2022 • Alexandra Peste, Adrian Vladu, Eldar Kurtic, Christoph H. Lampert, Dan Alistarh
In this work we propose a new compression-aware minimizer dubbed CrAM that modifies the optimization step in a principled way, in order to produce models whose local loss behavior is stable under compression operations such as pruning.
1 code implementation • CVPR 2022 • Eugenia Iofinova, Alexandra Peste, Mark Kurtz, Dan Alistarh
Transfer learning is a classic paradigm by which models pretrained on large "upstream" datasets are adapted to yield good results on "downstream" specialized datasets.
no code implementations • 8 Jul 2021 • Alexandra Peste, Dan Alistarh, Christoph H. Lampert
The availability of large amounts of user-provided data has been key to the success of machine learning for many real-world tasks.
2 code implementations • NeurIPS 2021 • Alexandra Peste, Eugenia Iofinova, Adrian Vladu, Dan Alistarh
The increasing computational requirements of deep neural networks (DNNs) have led to significant interest in obtaining DNN models that are sparse, yet accurate.
Ranked #1 on Network Pruning on CIFAR-100
no code implementations • 31 Jan 2021 • Torsten Hoefler, Dan Alistarh, Tal Ben-Nun, Nikoli Dryden, Alexandra Peste
The growing energy and performance costs of deep learning have driven the community to reduce the size of neural networks by selectively pruning components.