Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy

• URL: http://arxiv.org/abs/2103.03014v1
• Date: Thu, 4 Mar 2021 13:22:16 GMT
• Title: Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy
• Authors: Lucas Liebenwein, Cenk Baykal, Brandon Carter, David Gifford, Daniela Rus
• Abstract summary: Neural network pruning is a popular technique used to reduce the inference costs of modern networks. We evaluate whether the use of test accuracy alone in the terminating condition is sufficient to ensure that the resulting model performs well. We find that pruned networks effectively approximate the unpruned model, however, the prune ratio at which pruned networks achieve commensurate performance varies significantly across tasks.
• Score: 42.15969584135412
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Neural network pruning is a popular technique used to reduce the inference costs of modern, potentially overparameterized, networks. Starting from a pre-trained network, the process is as follows: remove redundant parameters, retrain, and repeat while maintaining the same test accuracy. The result is a model that is a fraction of the size of the original with comparable predictive performance (test accuracy). Here, we reassess and evaluate whether the use of test accuracy alone in the terminating condition is sufficient to ensure that the resulting model performs well across a wide spectrum of "harder" metrics such as generalization to out-of-distribution data and resilience to noise. Across evaluations on varying architectures and data sets, we find that pruned networks effectively approximate the unpruned model, however, the prune ratio at which pruned networks achieve commensurate performance varies significantly across tasks. These results call into question the extent of \emph{genuine} overparameterization in deep learning and raise concerns about the practicability of deploying pruned networks, specifically in the context of safety-critical systems, unless they are widely evaluated beyond test accuracy to reliably predict their performance. Our code is available at https://github.com/lucaslie/torchprune.

Related papers

• Quantifying lottery tickets under label noise: accuracy, calibration, and complexity [6.232071870655069]
  Pruning deep neural networks is a widely used strategy to alleviate the computational burden in machine learning. We use the sparse double descent approach to identify univocally and characterise pruned models associated with classification tasks.
  arXiv  Detail & Related papers  (2023-06-21T11:35:59Z)
• 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)
• Paoding: Supervised Robustness-preserving Data-free Neural Network Pruning [3.6953655494795776]
  We study the neural network pruning in the emphdata-free context. We replace the traditional aggressive one-shot strategy with a conservative one that treats the pruning as a progressive process. Our method is implemented as a Python package named textscPaoding and evaluated with a series of experiments on diverse neural network models.
  arXiv  Detail & Related papers  (2022-04-02T07:09:17Z)
• NUQ: Nonparametric Uncertainty Quantification for Deterministic Neural Networks [151.03112356092575]
  We show the principled way to measure the uncertainty of predictions for a classifier based on Nadaraya-Watson's nonparametric estimate of the conditional label distribution. We demonstrate the strong performance of the method in uncertainty estimation tasks on a variety of real-world image datasets.
  arXiv  Detail & Related papers  (2022-02-07T12:30:45Z)
• Mitigating Performance Saturation in Neural Marked Point Processes: Architectures and Loss Functions [50.674773358075015]
  We propose a simple graph-based network structure called GCHP, which utilizes only graph convolutional layers. We show that GCHP can significantly reduce training time and the likelihood ratio loss with interarrival time probability assumptions can greatly improve the model performance.
  arXiv  Detail & Related papers  (2021-07-07T16:59:14Z)
• Robustness to Pruning Predicts Generalization in Deep Neural Networks [29.660568281957072]
  We introduce prunability: the smallest emphfraction of a network's parameters that can be kept while pruning without adversely affecting its training loss. We show that this measure is highly predictive of a model's generalization performance across a large set of convolutional networks trained on CIFAR-10.
  arXiv  Detail & Related papers  (2021-03-10T11:39:14Z)
• Improving Uncertainty Calibration via Prior Augmented Data [56.88185136509654]
  Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. They are often overconfident in their predictions, which leads to inaccurate and miscalibrated probabilistic predictions. We propose a solution by seeking out regions of feature space where the model is unjustifiably overconfident, and conditionally raising the entropy of those predictions towards that of the prior distribution of the labels.
  arXiv  Detail & Related papers  (2021-02-22T07:02:37Z)
• Improving Video Instance Segmentation by Light-weight Temporal Uncertainty Estimates [11.580916951856256]
  We present a time-dynamic approach to model uncertainties of instance segmentation networks. We apply this approach to the detection of false positives and the estimation of prediction quality. The proposed method only requires a readily trained neural network and video sequence input.
  arXiv  Detail & Related papers  (2020-12-14T13:39:05Z)
• A Partial Regularization Method for Network Compression [0.0]
  We propose an approach of partial regularization rather than the original form of penalizing all parameters, which is said to be full regularization, to conduct model compression at a higher speed. Experimental results show that as we expected, the computational complexity is reduced by observing less running time in almost all situations. Surprisingly, it helps to improve some important metrics such as regression fitting results and classification accuracy in both training and test phases on multiple datasets.
  arXiv  Detail & Related papers  (2020-09-03T00:38:27Z)
• Uncertainty Estimation Using a Single Deep Deterministic Neural Network [66.26231423824089]
  We propose a method for training a deterministic deep model that can find and reject out of distribution data points at test time with a single forward pass. We scale training in these with a novel loss function and centroid updating scheme and match the accuracy of softmax models.
  arXiv  Detail & Related papers  (2020-03-04T12:27:36Z)

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.