2000 character limit reached
Embedding Differentiable Sparsity into Deep Neural Network (2006.13716v1)
Published 23 Jun 2020 in cs.LG and stat.ML
Abstract: In this paper, we propose embedding sparsity into the structure of deep neural networks, where model parameters can be exactly zero during training with the stochastic gradient descent. Thus, it can learn the sparsified structure and the weights of networks simultaneously. The proposed approach can learn structured as well as unstructured sparsity.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.