This invited survey reviews low-rank tensor decomposition and completion methods for compact uncertainty quantification and deep learning compression, with no new experimental or theoretical result.
MUSCO: Multi-Stage Compression of neural networks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
The low-rank tensor approximation is very promising for the compression of deep neural networks. We propose a new simple and efficient iterative approach, which alternates low-rank factorization with a smart rank selection and fine-tuning. We demonstrate the efficiency of our method comparing to non-iterative ones. Our approach improves the compression rate while maintaining the accuracy for a variety of tasks.
fields
math.OC 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Tensor Methods for Generating Compact Uncertainty Quantification and Deep Learning Models
This invited survey reviews low-rank tensor decomposition and completion methods for compact uncertainty quantification and deep learning compression, with no new experimental or theoretical result.