Loading...
Please wait, while we are loading the content...
An Analysis of Tensor Models for Learning on Structured Data
| Content Provider | CiteSeerX |
|---|---|
| Author | Tresp, Volker Nickel, Maximilian |
| Abstract | Abstract. While tensor factorizations have become increasingly popu-lar for learning on various forms of structured data, only very few theo-retical results exist on the generalization abilities of these methods. Here, we discuss the tensor product as a principled way to represent structured data in vector spaces for machine learning tasks. To derive generaliza-tion error bounds for tensor factorizations, we extend known bounds for matrix factorizations to the tensor case. Furthermore, we analyze exper-imentally and analytically how tensor factorization behaves for learning on over- and understructured representations, for instance, when matrix factorizations are applied to tensor data. |
| File Format | |
| Access Restriction | Open |
| Subject Keyword | Tensor Factorization Behaves Tensor Model Tensor Case Theo-retical Result Generalization Ability Understructured Representation Structured Data Generaliza-tion Error Tensor Factorization Machine Learning Task Matrix Factorization |
| Content Type | Text |
| Resource Type | Article |
