U.S. Department of Energy

Pacific Northwest National Laboratory

Tensor-Dictionary Learning with Deep Kruskal-Factor Analysis

Publish Date: 
Thursday, April 20, 2017
We introduce new dictionary learning methods for tensor-variate data of any order. We represent each data item as a sum of Kruskal decomposed dictionary atoms within the framework of beta-process factor analysis (BPFA). Our model is nonparametric and can infer the tensor-rank of each dictionary atom. This Kruskal-Factor Analysis (KFA) is a natural generalization of BPFA. We also extend KFA to a deep convolutional setting and develop online learning methods. We test our approach on image processing and classification tasks achieving state of the art results for 2D & 3D inpainting and Caltech 101. The experiments also show that atom-rank impacts both overcompleteness and sparsity.
Stevens AJ, Y Pu, Y Sun, G Spell, and L Carin. 2017. "Tensor-Dictionary Learning with Deep Kruskal-Factor Analysis." In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS 2017), April 20-22, 2017, Fort Lauderdale, Florida. No publisher listed.
| Pacific Northwest National Laboratory