Heuristic Rank Selection with Progressively Searching Tensor Ring Network

by   Nannan Li, et al.

Recently, Tensor Ring Networks (TRNs) have been applied in deep networks, achieving remarkable successes in compression ratio and accuracy. Although highly related to the performance of TRNs, rank is seldom studied in previous works and usually set to equal in experiments. Meanwhile, there is not any heuristic method to choose the rank, and an enumerating way to find appropriate rank is extremely time-consuming. Interestingly, we discover that part of the rank elements is sensitive and usually aggregate in a certain region, namely an interest region. Therefore, based on the above phenomenon, we propose a novel progressive genetic algorithm named Progressively Searching Tensor Ring Network Search (PSTRN), which has the ability to find optimal rank precisely and efficiently. Through the evolutionary phase and progressive phase, PSTRN can converge to the interest region quickly and harvest good performance. Experimental results show that PSTRN can significantly reduce the complexity of seeking rank, compared with the enumerating method. Furthermore, our method is validated on public benchmarks like MNIST, CIFAR10/100 and HMDB51, achieving state-of-the-art performance.



There are no comments yet.


page 1

page 2

page 3

page 4


Robust Tensor Recovery using Low-Rank Tensor Ring

Robust tensor completion recoveries the low-rank and sparse parts from i...

Hierarchical Tensor Ring Completion

Tensor completion can estimate missing values of a high-order data from ...

Semi-tensor Product-based TensorDecomposition for Neural Network Compression

The existing tensor networks adopt conventional matrix product for conne...

The trouble with tensor ring decompositions

The tensor train decomposition decomposes a tensor into a "train" of 3-w...

Robust M-estimation-based Tensor Ring Completion: a Half-quadratic Minimization Approach

Tensor completion is the problem of estimating the missing values of hig...

Wide Compression: Tensor Ring Nets

Deep neural networks have demonstrated state-of-the-art performance in a...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.