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.
Kishan Wimalawarne (Kyoto University)
Hiroshi Mamitsuka (Kyoto University)
More from the Same Authors
2019 Poster: AttentionXML: Label Tree-based Attention-Aware Deep Model for High-Performance Extreme Multi-Label Text Classification »
Ronghui You · Zihan Zhang · Ziye Wang · Suyang Dai · Hiroshi Mamitsuka · Shanfeng Zhu
2013 Poster: Manifold-based Similarity Adaptation for Label Propagation »
Masayuki Karasuyama · Hiroshi Mamitsuka