4 results found Sort:

48
317
apache-2.0
17
End-to-end training of sparse deep neural networks with little-to-no performance loss.
Created 2019-11-25
93 commits to master branch, last one 2 years ago
Always sparse. Never dense. But never say never. A Sparse Training repository for the Adaptive Sparse Connectivity concept and its algorithmic instantiation, i.e. Sparse Evolutionary Training, to boos...
Created 2018-03-02
26 commits to master branch, last one 3 years ago
[NeurIPS'21] "Chasing Sparsity in Vision Transformers: An End-to-End Exploration" by Tianlong Chen, Yu Cheng, Zhe Gan, Lu Yuan, Lei Zhang, Zhangyang Wang
Created 2021-05-28
9 commits to main branch, last one about a year ago
[ICML 2021] "Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training" by Shiwei Liu, Lu Yin, Decebal Constantin Mocanu, Mykola Pechenizkiy
Created 2021-06-10
70 commits to main branch, last one about a year ago