Recursive Least Squares for Training and Pruning Convolutional Neural Networks

By Tianzong Yu, Chunyuan Zhang, Yuan Wang, Meng-tao Ma, Qingwei Song. 2022

Convolutional neural networks (CNNs) have succeeded in many practical applications. However, their high computation and storage requirements often make them difficult to deploy on resource-constrained devices. In order to tackle this issue, many pruning algorithms have been proposed for CNNs, but most of them can't prune CNNs to a reasonable level. In this paper, we propose a novel algorithm for training and pruning CNNs based on the recursive least squares (RLS) optimization. After training a CNN for some epochs, our algorithm combines inverse input autocorrelation matrices and weight matrices to evaluate and prune unimportant input channels or nodes layer by layer. Then, our algorithm will continue to train the pruned network, and won't do the next pruning until the pruned network recovers the full performance of the old network. Besides for CNNs, the proposed algorithm can be used for feedforward neural networks (FNNs). Three experiments on MNIST, CIFAR-10 and SVHN datasets show that our algorithm can achieve the more reasonable pruning and have higher learning efficiency than other four popular pruning algorithms.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Youngjae Min
2. Kwangjun Ahn
3. Navid Azizan
4. Namhoon Cho

Citations in the corpus

• One-Pass Learning via Bridging Orthogonal Gradient Descent and Recursive Least-Squares (2022, positive): “Related to the overparameterized setting, a few works have recently discussed utilizing RLS to train popular deep neural networks [19], [20].”