Neural Pruning via Growing Regularization

• URL: http://arxiv.org/abs/2012.09243v2
• Date: Mon, 5 Apr 2021 19:37:45 GMT
• Title: Neural Pruning via Growing Regularization
• Authors: Huan Wang, Can Qin, Yulun Zhang, Yun Fu
• Abstract summary: We extend regularization to tackle two central problems of pruning: pruning schedule and weight importance scoring. Specifically, we propose an L2 regularization variant with rising penalty factors and show it can bring significant accuracy gains. The proposed algorithms are easy to implement and scalable to large datasets and networks in both structured and unstructured pruning.
• Score: 82.9322109208353
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Regularization has long been utilized to learn sparsity in deep neural network pruning. However, its role is mainly explored in the small penalty strength regime. In this work, we extend its application to a new scenario where the regularization grows large gradually to tackle two central problems of pruning: pruning schedule and weight importance scoring. (1) The former topic is newly brought up in this work, which we find critical to the pruning performance while receives little research attention. Specifically, we propose an L2 regularization variant with rising penalty factors and show it can bring significant accuracy gains compared with its one-shot counterpart, even when the same weights are removed. (2) The growing penalty scheme also brings us an approach to exploit the Hessian information for more accurate pruning without knowing their specific values, thus not bothered by the common Hessian approximation problems. Empirically, the proposed algorithms are easy to implement and scalable to large datasets and networks in both structured and unstructured pruning. Their effectiveness is demonstrated with modern deep neural networks on the CIFAR and ImageNet datasets, achieving competitive results compared to many state-of-the-art algorithms. Our code and trained models are publicly available at https://github.com/mingsuntse/regularization-pruning.

Related papers

• Iterative Soft Shrinkage Learning for Efficient Image Super-Resolution [91.3781512926942]
  Image super-resolution (SR) has witnessed extensive neural network designs from CNN to transformer architectures. This work investigates the potential of network pruning for super-resolution iteration to take advantage of off-the-shelf network designs and reduce the underlying computational overhead. We propose a novel Iterative Soft Shrinkage-Percentage (ISS-P) method by optimizing the sparse structure of a randomly network at each and tweaking unimportant weights with a small amount proportional to the magnitude scale on-the-fly.
  arXiv  Detail & Related papers  (2023-03-16T21:06:13Z)
• Can pruning improve certified robustness of neural networks? [106.03070538582222]
  We show that neural network pruning can improve empirical robustness of deep neural networks (NNs) Our experiments show that by appropriately pruning an NN, its certified accuracy can be boosted up to 8.2% under standard training. We additionally observe the existence of certified lottery tickets that can match both standard and certified robust accuracies of the original dense models.
  arXiv  Detail & Related papers  (2022-06-15T05:48:51Z)
• RED : Looking for Redundancies for Data-Free Structured Compression of Deep Neural Networks [36.027765880474526]
  We present RED, a data-free structured, unified approach to tackle structured pruning. First, we propose a novel adaptive hashing of the scalar weight distribution densities to increase the number of identical neurons. Second, we prune the network by merging redundant neurons based on their relative similarities, as defined by their distance. Third, we propose a novel uneven depthwise separation technique to further prune convolutional layers.
  arXiv  Detail & Related papers  (2021-05-31T08:44:14Z)
• Emerging Paradigms of Neural Network Pruning [82.9322109208353]
  Pruning is adopted as a post-processing solution to this problem, which aims to remove unnecessary parameters in a neural network with little performance compromised. Recent works challenge this belief by discovering random sparse networks which can be trained to match the performance with their dense counterpart. This survey seeks to bridge the gap by proposing a general pruning framework so that the emerging pruning paradigms can be accommodated well with the traditional one.
  arXiv  Detail & Related papers  (2021-03-11T05:01:52Z)
• SRDCNN: Strongly Regularized Deep Convolution Neural Network Architecture for Time-series Sensor Signal Classification Tasks [4.950427992960756]
  We present SRDCNN: Strongly Regularized Deep Convolution Neural Network (DCNN) based deep architecture to perform time series classification tasks. The novelty of the proposed approach is that the network weights are regularized by both L1 and L2 norm penalties.
  arXiv  Detail & Related papers  (2020-07-14T08:42:39Z)
• Progressive Skeletonization: Trimming more fat from a network at initialization [76.11947969140608]
  We propose an objective to find a skeletonized network with maximum connection sensitivity. We then propose two approximate procedures to maximize our objective. Our approach provides remarkably improved performance on higher pruning levels.
  arXiv  Detail & Related papers  (2020-06-16T11:32:47Z)
• WoodFisher: Efficient Second-Order Approximation for Neural Network Compression [35.45199662813043]
  We develop a method to compute a faithful and efficient estimate of the inverse Hessian. Our main application is to neural network compression. We show how our method can be extended to take into account first-order information.
  arXiv  Detail & Related papers  (2020-04-29T17:14:23Z)
• How Not to Give a FLOP: Combining Regularization and Pruning for Efficient Inference [0.0]
  In this paper, we examine the use of both regularization and pruning for reduced computational complexity and more efficient inference in Deep Neural Networks (DNNs) By using regularization in conjunction with network pruning, we show that such a combination makes a substantial improvement over each of the two techniques individually.
  arXiv  Detail & Related papers  (2020-03-30T16:20:46Z)
• Distance-Based Regularisation of Deep Networks for Fine-Tuning [116.71288796019809]
  We develop an algorithm that constrains a hypothesis class to a small sphere centred on the initial pre-trained weights. Empirical evaluation shows that our algorithm works well, corroborating our theoretical results.
  arXiv  Detail & Related papers  (2020-02-19T16:00:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.