NEPENTHE: Entropy-Based Pruning as a Neural Network Depth's Reducer

• URL: http://arxiv.org/abs/2404.16890v1
• Date: Wed, 24 Apr 2024 09:12:04 GMT
• Title: NEPENTHE: Entropy-Based Pruning as a Neural Network Depth's Reducer
• Authors: Zhu Liao, Victor Quétu, Van-Tam Nguyen, Enzo Tartaglione,
• Abstract summary: We propose an eNtropy-basEd Pruning as a nEural Network depTH's rEducer to alleviate deep neural networks' computational burden. We validate our approach on popular architectures such as MobileNet and Swin-T.
• Score: 5.373015313199385
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While deep neural networks are highly effective at solving complex tasks, their computational demands can hinder their usefulness in real-time applications and with limited-resources systems. Besides, for many tasks it is known that these models are over-parametrized: neoteric works have broadly focused on reducing the width of these networks, rather than their depth. In this paper, we aim to reduce the depth of over-parametrized deep neural networks: we propose an eNtropy-basEd Pruning as a nEural Network depTH's rEducer (NEPENTHE) to alleviate deep neural networks' computational burden. Based on our theoretical finding, NEPENTHE focuses on un-structurally pruning connections in layers with low entropy to remove them entirely. We validate our approach on popular architectures such as MobileNet and Swin-T, showing that when encountering an over-parametrization regime, it can effectively linearize some layers (hence reducing the model's depth) with little to no performance loss. The code will be publicly available upon acceptance of the article.

Related papers

• LaCoOT: Layer Collapse through Optimal Transport [5.869633234882029]
  We present an optimal transport method to reduce the depth of over-parametrized deep neural networks. We show that minimizing this distance enables the complete removal of intermediate layers in the network, with almost no performance loss and without requiring any finetuning.
  arXiv  Detail & Related papers  (2024-06-13T09:03:53Z)
• The Simpler The Better: An Entropy-Based Importance Metric To Reduce Neural Networks' Depth [5.869633234882029]
  We propose an efficiency strategy that leverages prior knowledge transferred by large models. Simple but effective, we propose a method relying on an Entropy-bASed Importance mEtRic (EASIER) to reduce the depth of over-parametrized deep neural networks.
  arXiv  Detail & Related papers  (2024-04-27T08:28:25Z)
• Can Unstructured Pruning Reduce the Depth in Deep Neural Networks? [5.869633234882029]
  Pruning is a widely used technique for reducing the size of deep neural networks while maintaining their performance. In this study, we introduce EGP, an innovative Entropy Guided Pruning algorithm aimed at reducing the size of deep neural networks while preserving their performance.
  arXiv  Detail & Related papers  (2023-08-12T17:27:49Z)
• 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)
• Provable Regret Bounds for Deep Online Learning and Control [77.77295247296041]
  We show that any loss functions can be adapted to optimize the parameters of a neural network such that it competes with the best net in hindsight. As an application of these results in the online setting, we obtain provable bounds for online control controllers.
  arXiv  Detail & Related papers  (2021-10-15T02:13:48Z)
• Building Compact and Robust Deep Neural Networks with Toeplitz Matrices [93.05076144491146]
  This thesis focuses on the problem of training neural networks which are compact, easy to train, reliable and robust to adversarial examples. We leverage the properties of structured matrices from the Toeplitz family to build compact and secure neural networks.
  arXiv  Detail & Related papers  (2021-09-02T13:58:12Z)
• Layer Folding: Neural Network Depth Reduction using Activation Linearization [0.0]
  Modern devices exhibit a high level of parallelism, but real-time latency is still highly dependent on networks' depth. We propose a method that learns whether non-linear activations can be removed, allowing to fold consecutive linear layers into one. We apply our method to networks pre-trained on CIFAR-10 and CIFAR-100 and find that they can all be transformed into shallower forms that share a similar depth.
  arXiv  Detail & Related papers  (2021-06-17T08:22:46Z)
• 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)
• Rectified Linear Postsynaptic Potential Function for Backpropagation in Deep Spiking Neural Networks [55.0627904986664]
  Spiking Neural Networks (SNNs) usetemporal spike patterns to represent and transmit information, which is not only biologically realistic but also suitable for ultra-low-power event-driven neuromorphic implementation. This paper investigates the contribution of spike timing dynamics to information encoding, synaptic plasticity and decision making, providing a new perspective to design of future DeepSNNs and neuromorphic hardware systems.
  arXiv  Detail & Related papers  (2020-03-26T11:13:07Z)
• Beyond Dropout: Feature Map Distortion to Regularize Deep Neural Networks [107.77595511218429]
  In this paper, we investigate the empirical Rademacher complexity related to intermediate layers of deep neural networks. We propose a feature distortion method (Disout) for addressing the aforementioned problem. The superiority of the proposed feature map distortion for producing deep neural network with higher testing performance is analyzed and demonstrated.
  arXiv  Detail & Related papers  (2020-02-23T13:59:13Z)
• Lossless Compression of Deep Neural Networks [17.753357839478575]
  Deep neural networks have been successful in many predictive modeling tasks, such as image and language recognition. It is challenging to deploy these networks under limited computational resources, such as in mobile devices. We introduce an algorithm that removes units and layers of a neural network while not changing the output that is produced.
  arXiv  Detail & Related papers  (2020-01-01T15:04:43Z)

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.