Title | ||
---|---|---|
Performance Analysis for Tensor-Train Decomposition to Deep Neural Network Based Vector-to-Vector Regression |
Abstract | ||
---|---|---|
This work focuses on a performance analysis of tensor-train decomposition applied to the deep neural network (DNN) based vector-to-vector regression. Tensor-train Network (TTN), obtained through tensor-train decomposition, converts a DNN based vector-to-vector regression into a tensor-to-vector mapping with fewer parameters. We can therefore build an over-parametrized DNN with the tensor-train representation such that the optimization error can be significantly reduced, while the upper bounds on the approximation and estimation errors can be maintained. We compare TTN-based neural architecture against an over-parametrized DNN on the MNIST dataset, and the experimental evidence demonstrates the validity of our conjectures on our proposed performance bounds. |
Year | DOI | Venue |
---|---|---|
2020 | 10.1109/CISS48834.2020.1570617364 | 2020 54th Annual Conference on Information Sciences and Systems (CISS) |
Keywords | DocType | ISBN |
Tensor-train decomposition,deep neural network,vector-to-vector regression,over-parameterization,tensorto-vector regression | Conference | 978-1-7281-8831-7 |
Citations | PageRank | References |
0 | 0.34 | 6 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jun Qi | 1 | 11 | 3.96 |
Xiaoli Ma | 2 | 1412 | 105.25 |
Chin-Hui Lee | 3 | 6101 | 852.71 |
Jun Du | 4 | 76 | 17.84 |
Sabato Marco Siniscalchi | 5 | 310 | 30.21 |