# Robust Deep Networks with Randomized Tensor Regression Layers

27 Feb 2019Arinbjörn KolbeinssonJean KossaifiYannis PanagakisAdrian BulatAnima AnandkumarIoanna TzoulakiPaul Matthews

In this paper, we propose a novel randomized tensor decomposition for tensor regression. It allows to stochastically approximate the weights of tensor regression layers by randomly sampling in the low-rank subspace... (read more)

PDF Abstract