Convex Tensor Decomposition via Structured Schatten Norm Regularization

Abstract

We study a new class of structured Schatten norms for tensors that includes two recently proposed norms (“overlapped” and “latent”) for convex-optimization-based tensor decomposition. Based on the properties of the structured Schatten norms, we analyze the performance of “latent” approach for tensor decomposition, which was empirically found to perform… (More)

Topics

2 Figures and Tables

Cite this paper

@inproceedings{Tomioka2013ConvexTD, title={Convex Tensor Decomposition via Structured Schatten Norm Regularization}, author={Ryota Tomioka and Taiji Suzuki}, booktitle={NIPS}, year={2013} }