Tensor shape search for efficient compression of tensorized data and neural networks

Ryan Solgi, Zichang He, William Jiahua Liang, Zheng Zhang, Hugo A. Loáiciga

Abstract: Highlights•The effect of tensor reshaping is studied for the tensor train (TT) compression.•The space-saving of tensor compression is optimized with respect to the tensor shape.•A genetic algorithm (GA) is applied to solve the tensor shape optimization problem.•The proposed model is applied to compress data and tensorized neural networks.