Confident magnitude-based neural network pruning

• URL: http://arxiv.org/abs/2408.04759v1
• Date: Thu, 8 Aug 2024 21:29:20 GMT
• Title: Confident magnitude-based neural network pruning
• Authors: Joaquin Alvarez,
• Abstract summary: Pruning neural networks has proven to be a successful approach to increase the efficiency and reduce the memory storage of deep learning models. We leverage recent techniques on distribution-free uncertainty quantification to provide finite-sample statistical guarantees to compress deep neural networks. This work presents experiments in computer vision tasks to illustrate how uncertainty-aware pruning is a useful approach to deploy sparse neural networks safely.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Pruning neural networks has proven to be a successful approach to increase the efficiency and reduce the memory storage of deep learning models without compromising performance. Previous literature has shown that it is possible to achieve a sizable reduction in the number of parameters of a deep neural network without deteriorating its predictive capacity in one-shot pruning regimes. Our work builds beyond this background in order to provide rigorous uncertainty quantification for pruning neural networks reliably, which has not been addressed to a great extent in previous literature focusing on pruning methods in computer vision settings. We leverage recent techniques on distribution-free uncertainty quantification to provide finite-sample statistical guarantees to compress deep neural networks, while maintaining high performance. Moreover, this work presents experiments in computer vision tasks to illustrate how uncertainty-aware pruning is a useful approach to deploy sparse neural networks safely.

Related papers

• Tractable Function-Space Variational Inference in Bayesian Neural Networks [72.97620734290139]
  A popular approach for estimating the predictive uncertainty of neural networks is to define a prior distribution over the network parameters. We propose a scalable function-space variational inference method that allows incorporating prior information. We show that the proposed method leads to state-of-the-art uncertainty estimation and predictive performance on a range of prediction tasks.
  arXiv  Detail & Related papers  (2023-12-28T18:33:26Z)
• Pruning a neural network using Bayesian inference [1.776746672434207]
  Neural network pruning is a highly effective technique aimed at reducing the computational and memory demands of large neural networks. We present a novel approach to pruning neural networks utilizing Bayesian inference, which can seamlessly integrate into the training procedure.
  arXiv  Detail & Related papers  (2023-08-04T16:34:06Z)
• Addressing caveats of neural persistence with deep graph persistence [54.424983583720675]
  We find that the variance of network weights and spatial concentration of large weights are the main factors that impact neural persistence. We propose an extension of the filtration underlying neural persistence to the whole neural network instead of single layers. This yields our deep graph persistence measure, which implicitly incorporates persistent paths through the network and alleviates variance-related issues.
  arXiv  Detail & Related papers  (2023-07-20T13:34:11Z)
• Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks [23.7125322065694]
  Uncertainty quantification (UQ) is important for reliability assessment and enhancement of machine learning models. We create statistically guaranteed schemes to principally emphcharacterize, and emphremove, the uncertainty of over- parameterized neural networks. In particular, our approach, based on what we call a procedural-noise-correcting (PNC) predictor, removes the procedural uncertainty by using only emphone auxiliary network that is trained on a suitably labeled dataset.
  arXiv  Detail & Related papers  (2023-06-09T05:15:53Z)
• 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)
• 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)
• Neural Network Pruning Through Constrained Reinforcement Learning [3.2880869992413246]
  We propose a general methodology for pruning neural networks. Our proposed methodology can prune neural networks to respect pre-defined computational budgets. We prove the effectiveness of our approach via comparison with state-of-the-art methods on standard image classification datasets.
  arXiv  Detail & Related papers  (2021-10-16T11:57:38Z)
• Sparse Deep Learning: A New Framework Immune to Local Traps and Miscalibration [12.05471394131891]
  We provide a new framework for sparse deep learning, which has the above issues addressed in a coherent way. We lay down a theoretical foundation for sparse deep learning and propose prior annealing algorithms for learning sparse neural networks.
  arXiv  Detail & Related papers  (2021-10-01T21:16:34Z)
• Residual Error: a New Performance Measure for Adversarial Robustness [85.0371352689919]
  A major challenge that limits the wide-spread adoption of deep learning has been their fragility to adversarial attacks. This study presents the concept of residual error, a new performance measure for assessing the adversarial robustness of a deep neural network. Experimental results using the case of image classification demonstrate the effectiveness and efficacy of the proposed residual error metric.
  arXiv  Detail & Related papers  (2021-06-18T16:34:23Z)
• ESPN: Extremely Sparse Pruned Networks [50.436905934791035]
  We show that a simple iterative mask discovery method can achieve state-of-the-art compression of very deep networks. Our algorithm represents a hybrid approach between single shot network pruning methods and Lottery-Ticket type approaches.
  arXiv  Detail & Related papers  (2020-06-28T23:09:27Z)
• Approximation smooth and sparse functions by deep neural networks without saturation [0.6396288020763143]
  In this paper, we aim at constructing deep neural networks with three hidden layers to approximate smooth and sparse functions. We prove that the constructed deep nets can reach the optimal approximation rate in approximating both smooth and sparse functions with controllable magnitude of free parameters.
  arXiv  Detail & Related papers  (2020-01-13T09:28:50Z)

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.