%0 Generic %1 cao2017tensor %A Cao, Xingwei %A Rabusseau, Guillaume %A Pineau, Joelle %D 2017 %K networks neural %T Tensor Regression Networks with various Low-Rank Tensor Approximations %U http://arxiv.org/abs/1712.09520 %X Tensor regression networks achieve high rate of compression of model parameters in multilayer perceptrons (MLP) while having slight impact on performances. Tensor regression layer imposes low-rank constraints on the tensor regression layer which replaces the flattening operation of traditional MLP. We investigate tensor regression networks using various low-rank tensor approximations, aiming to leverage the multi-modal structure of high dimensional data by enforcing efficient low-rank constraints. We provide a theoretical analysis giving insights on the choice of the rank parameters. We evaluated performance of proposed model with state-of-the-art deep convolutional models. For CIFAR-10 dataset, we achieved the compression rate of 0.018 with the sacrifice of accuracy less than 1%.

@misc{cao2017tensor, abstract = {Tensor regression networks achieve high rate of compression of model parameters in multilayer perceptrons (MLP) while having slight impact on performances. Tensor regression layer imposes low-rank constraints on the tensor regression layer which replaces the flattening operation of traditional MLP. We investigate tensor regression networks using various low-rank tensor approximations, aiming to leverage the multi-modal structure of high dimensional data by enforcing efficient low-rank constraints. We provide a theoretical analysis giving insights on the choice of the rank parameters. We evaluated performance of proposed model with state-of-the-art deep convolutional models. For CIFAR-10 dataset, we achieved the compression rate of 0.018 with the sacrifice of accuracy less than 1%.}, added-at = {2018-04-12T17:44:24.000+0200}, author = {Cao, Xingwei and Rabusseau, Guillaume and Pineau, Joelle}, biburl = {https://www.bibsonomy.org/bibtex/28f66a13160990ece8bf7ef17a48c3c72/pavelkrolevets}, description = {Tensor Regression Networks with various Low-Rank Tensor Approximations}, interhash = {efc836f6e77175f6212c12d376403cbf}, intrahash = {8f66a13160990ece8bf7ef17a48c3c72}, keywords = {networks neural}, note = {cite arxiv:1712.09520}, timestamp = {2018-04-12T17:44:24.000+0200}, title = {Tensor Regression Networks with various Low-Rank Tensor Approximations}, url = {http://arxiv.org/abs/1712.09520}, year = 2017 }