It is regarded as a promising distributed and privacy-preserving method.

Existing regularization methods merely minimize the norms of embeddings to regularize the model, leading to suboptimal performance.

Neural Information Processing Systems http://nips.cc/

Structured matrix recovery has found a wide spectrum of applications in real world, e.g., recommender

Coupled norms have emerged as a convex method to solve coupled tensor completion. A limitation with coupled norms is that they only induce low-rankness using the multilinear rank of coupled tensors. In this paper, we introduce a new set of coupled norms known as coupled nuclear norms by constraining the CP rank of coupled tensors. We propose new coupled completion models using the coupled nuclear norms as regularizers, which can be optimized using computationally efficient optimization methods. We derive excess risk bounds for proposed coupled completion models and show that proposed norms lead to better performance. Through simulation and real-data experiments, we demonstrate that proposed norms achieve better performance for coupled completion compared to existing coupled norms.

We develop a dual framework for solving the low-rank tensor completion problem.

We develop a dual framework for solving the low-rank tensor completion problem.

Existing regularization methods merely minimize the norms of embeddings to regularize the model, leading to suboptimal performance.

It is regarded as a promising distributed and privacy-preserving method.