Corpus ID: 236772123

Pruning Neural Networks with Interpolative Decompositions

  title={Pruning Neural Networks with Interpolative Decompositions},
  author={Jerry Chee and Megan Renz and Anil Damle and Chris De Sa},
We introduce a principled approach to neural network pruning that casts the problem as a structured low-rank matrix approximation. Our method uses a novel application of a matrix factorization technique called the interpolative decomposition to approximate the activation output of a network layer. This technique selects neurons or channels in the layer and propagates a corrective interpolation matrix to the next layer, resulting in a dense, pruned network with minimal degradation before fine… Expand

Figures and Tables from this paper


Speeding-up Convolutional Neural Networks Using Fine-tuned CP-Decomposition
A simple two-step approach for speeding up convolution layers within large convolutional neural networks based on tensor decomposition and discriminative fine-tuning is proposed, leading to higher obtained CPU speedups at the cost of lower accuracy drops for the smaller of the two networks. Expand
Data-Driven Sparse Structure Selection for Deep Neural Networks
A simple and effective framework to learn and prune deep models in an end-to-end manner by adding sparsity regularizations on factors, and solving the optimization problem by a modified stochastic Accelerated Proximal Gradient (APG) method. Expand
ThiNet: A Filter Level Pruning Method for Deep Neural Network Compression
ThiNet is proposed, an efficient and unified framework to simultaneously accelerate and compress CNN models in both training and inference stages, and it is revealed that it needs to prune filters based on statistics information computed from its next layer, not the current layer, which differentiates ThiNet from existing methods. Expand
Channel Pruning for Accelerating Very Deep Neural Networks
  • Yihui He, X. Zhang, Jian Sun
  • Computer Science
  • 2017 IEEE International Conference on Computer Vision (ICCV)
  • 2017
This paper proposes an iterative two-step algorithm to effectively prune each layer, by a LASSO regression based channel selection and least square reconstruction, and generalizes this algorithm to multi-layer and multi-branch cases. Expand
Pruning Filters for Efficient ConvNets
This work presents an acceleration method for CNNs, where it is shown that even simple filter pruning techniques can reduce inference costs for VGG-16 and ResNet-110 by up to 38% on CIFAR10 while regaining close to the original accuracy by retraining the networks. Expand
Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Acceleration
Unlike previous methods, FPGM compresses CNN models by pruning filters with redundancy, rather than those with“relatively less” importance, and when applied to two image classification benchmarks, the method validates its usefulness and strengths. Expand
Discrimination-aware Channel Pruning for Deep Neural Networks
This work investigates a simple-yet-effective method, called discrimination-aware channel pruning, to choose those channels that really contribute to discriminative power and proposes a greedy algorithm to conduct channel selection and parameter optimization in an iterative way. Expand
Data-Independent Neural Pruning via Coresets
This work proposes the first efficient, data-independent neural pruning algorithm with a provable trade-off between its compression rate and the approximation error for any future test sample, and demonstrates the effectiveness of the method on popular network architectures. Expand
Learning Efficient Convolutional Networks through Network Slimming
The approach is called network slimming, which takes wide and large networks as input models, but during training insignificant channels are automatically identified and pruned afterwards, yielding thin and compact models with comparable accuracy. Expand
Rethinking the Value of Network Pruning
It is found that with optimal learning rate, the "winning ticket" initialization as used in Frankle & Carbin (2019) does not bring improvement over random initialization, and the need for more careful baseline evaluations in future research on structured pruning methods is suggested. Expand