arXiv Analytics

Sign in

arXiv:1807.03165 [cs.LG]AbstractReferencesReviewsResources

Sparse Deep Neural Network Exact Solutions

Jeremy Kepner, Vijay Gadepally, Hayden Jananthan, Lauren Milechin, Sid Samsi

Published 2018-07-06Version 1

Deep neural networks (DNNs) have emerged as key enablers of machine learning. Applying larger DNNs to more diverse applications is an important challenge. The computations performed during DNN training and inference are dominated by operations on the weight matrices describing the DNN. As DNNs incorporate more layers and more neurons per layers, these weight matrices may be required to be sparse because of memory limitations. Sparse DNNs are one possible approach, but the underlying theory is in the early stages of development and presents a number of challenges, including determining the accuracy of inference and selecting nonzero weights for training. Associative array algebra has been developed by the big data community to combine and extend database, matrix, and graph/network concepts for use in large, sparse data problems. Applying this mathematics to DNNs simplifies the formulation of DNN mathematics and reveals that DNNs are linear over oscillating semirings. This work uses associative array DNNs to construct exact solutions and corresponding perturbation models to the rectified linear unit (ReLU) DNN equations that can be used to construct test vectors for sparse DNN implementations over various precisions. These solutions can be used for DNN verification, theoretical explorations of DNN properties, and a starting point for the challenge of sparse training.

Comments: 8 pages, 10 figures, accepted to IEEE HPEC 2018. arXiv admin note: text overlap with arXiv:1708.02937
Categories: cs.LG, cs.CV, cs.NE, stat.ML
Related articles: Most relevant | Search more
arXiv:1206.4639 [cs.LG] (Published 2012-06-18)
Adaptive Regularization for Weight Matrices
arXiv:1703.00144 [cs.LG] (Published 2017-03-01)
Theoretical Properties for Neural Networks with Weight Matrices of Low Displacement Rank
arXiv:2010.04963 [cs.LG] (Published 2020-10-10)
Block-term Tensor Neural Networks