Data-Independent Neural Pruning via Coresets
作者： Vladimir Braverman , Margarita Osadchy , Dan Feldman , Samson Zhou , Ben Mussay
DOI:
关键词:
摘要: Previous work showed empirically that large neural networks can be significantly reduced in size while preserving their accuracy. Model compression became a central research topic …
harvard.edu
arxiv.org参考文章(31)
Michael Langberg, Leonard J. Schulman, Universal epsilon-approximators for Integrals. symposium on discrete algorithms. pp. 598- 607 ,(2010)
Vadim Lebedev, Victor Lempitsky, Fast ConvNets Using Group-Wise Brain Damage computer vision and pattern recognition. pp. 2554- 2564 ,(2016) , 10.1109/CVPR.2016.280
Martin Anthony, Peter L Bartlett, Peter L Bartlett, Neural Network Learning: Theoretical Foundations ,(1999)
Dan Feldman, Michael Langberg, A unified framework for approximating and clustering data symposium on the theory of computing. pp. 569- 578 ,(2011) , 10.1145/1993636.1993712
V. N. Vapnik, A. Ya. Chervonenkis, On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities Measures of Complexity. ,vol. 16, pp. 11- 30 ,(2015) , 10.1007/978-3-319-21852-6_3
Ilya Sutskever, Geoffrey Hinton, Alex Krizhevsky, Ruslan Salakhutdinov, Nitish Srivastava, Dropout: a simple way to prevent neural networks from overfitting Journal of Machine Learning Research. ,vol. 15, pp. 1929- 1958 ,(2014)
Y. Lecun, L. Bottou, Y. Bengio, P. Haffner, Gradient-based learning applied to document recognition Proceedings of the IEEE. ,vol. 86, pp. 2278- 2324 ,(1998) , 10.1109/5.726791
Yann LeCun, John Denker, Sara Solla, None, Optimal Brain Damage neural information processing systems. ,vol. 2, pp. 598- 605 ,(1989)
Paul Smolensky, Michael C. Mozer, Skeletonization: A Technique for Trimming the Fat from a Network via Relevance Assessment neural information processing systems. ,vol. 1, pp. 107- 115 ,(1988)
Emily L Denton, Yann LeCun, Joan Bruna, Rob Fergus, Wojciech Zaremba, Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation neural information processing systems. ,vol. 27, pp. 1269- 1277 ,(2014)