Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations

• URL: http://arxiv.org/abs/2110.08271v1
• Date: Fri, 15 Oct 2021 16:14:36 GMT
• Title: Training Deep Neural Networks with Joint Quantization and Pruning of Weights and Activations
• Authors: Xinyu Zhang, Ian Colbert, Ken Kreutz-Delgado, Srinjoy Das
• Abstract summary: State-of-the-art quantization techniques are currently applied to both the weights and activations of deep neural networks. In this work, we jointly apply novel uniform quantization and unstructured pruning methods to both the weights and activations of deep neural networks during training.
• Score: 5.17729871332369
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Quantization and pruning are core techniques used to reduce the inference costs of deep neural networks. State-of-the-art quantization techniques are currently applied to both the weights and activations; however, pruning is most often applied to only the weights of the network. In this work, we jointly apply novel uniform quantization and unstructured pruning methods to both the weights and activations of deep neural networks during training. Using our methods, we empirically evaluate the currently accepted prune-then-quantize paradigm across a wide range of computer vision tasks and observe a non-commutative nature when applied to both the weights and activations of deep neural networks. Informed by these observations, we articulate the non-commutativity hypothesis: for a given deep neural network being trained for a specific task, there exists an exact training schedule in which quantization and pruning can be introduced to optimize network performance. We identify that this optimal ordering not only exists, but also varies across discriminative and generative tasks. Using the optimal training schedule within our training framework, we demonstrate increased performance per memory footprint over existing solutions.

Related papers

• Neural Networks Trained by Weight Permutation are Universal Approximators [4.642647756403863]
  We show that a permutation-based training method can guide a ReLU network to approximate one-dimensional continuous functions. The notable observations during weight permutation suggest that permutation training can provide an innovative tool for describing network learning behavior.
  arXiv  Detail & Related papers  (2024-07-01T07:33:00Z)
• Enhanced quantum state preparation via stochastic prediction of neural network [0.8287206589886881]
  In this paper, we explore an intriguing avenue for enhancing algorithm effectiveness through exploiting the knowledge blindness of neural network. Our approach centers around a machine learning algorithm utilized for preparing arbitrary quantum states in a semiconductor double quantum dot system. By leveraging prediction generated by the neural network, we are able to guide the optimization process to escape local optima.
  arXiv  Detail & Related papers  (2023-07-27T09:11:53Z)
• Globally Optimal Training of Neural Networks with Threshold Activation Functions [63.03759813952481]
  We study weight decay regularized training problems of deep neural networks with threshold activations. We derive a simplified convex optimization formulation when the dataset can be shattered at a certain layer of the network.
  arXiv  Detail & Related papers  (2023-03-06T18:59:13Z)
• Quantization-aware Interval Bound Propagation for Training Certifiably Robust Quantized Neural Networks [58.195261590442406]
  We study the problem of training and certifying adversarially robust quantized neural networks (QNNs) Recent work has shown that floating-point neural networks that have been verified to be robust can become vulnerable to adversarial attacks after quantization. We present quantization-aware interval bound propagation (QA-IBP), a novel method for training robust QNNs.
  arXiv  Detail & Related papers  (2022-11-29T13:32:38Z)
• Neural Network Panning: Screening the Optimal Sparse Network Before Training [15.349144733875368]
  We argue that network pruning can be summarized as an expressive force transfer process of weights. We propose a pruning scheme before training called Neural Network Panning which guides expressive force transfer through multi-index and multi-process steps.
  arXiv  Detail & Related papers  (2022-09-27T13:31:43Z)
• The Multiple Subnetwork Hypothesis: Enabling Multidomain Learning by Isolating Task-Specific Subnetworks in Feedforward Neural Networks [0.0]
  We identify a methodology and network representational structure which allows a pruned network to employ previously unused weights to learn subsequent tasks. We show that networks trained using our approaches are able to learn multiple tasks, which may be related or unrelated, in parallel or in sequence without sacrificing performance on any task or exhibiting catastrophic forgetting.
  arXiv  Detail & Related papers  (2022-07-18T15:07:13Z)
• Dynamic Neural Diversification: Path to Computationally Sustainable Neural Networks [68.8204255655161]
  Small neural networks with a constrained number of trainable parameters, can be suitable resource-efficient candidates for many simple tasks. We explore the diversity of the neurons within the hidden layer during the learning process. We analyze how the diversity of the neurons affects predictions of the model.
  arXiv  Detail & Related papers  (2021-09-20T15:12:16Z)
• What can linearized neural networks actually say about generalization? [67.83999394554621]
  In certain infinitely-wide neural networks, the neural tangent kernel (NTK) theory fully characterizes generalization. We show that the linear approximations can indeed rank the learning complexity of certain tasks for neural networks. Our work provides concrete examples of novel deep learning phenomena which can inspire future theoretical research.
  arXiv  Detail & Related papers  (2021-06-12T13:05:11Z)
• Ps and Qs: Quantization-aware pruning for efficient low latency neural network inference [56.24109486973292]
  We study the interplay between pruning and quantization during the training of neural networks for ultra low latency applications. We find that quantization-aware pruning yields more computationally efficient models than either pruning or quantization alone for our task.
  arXiv  Detail & Related papers  (2021-02-22T19:00:05Z)
• Recurrence of Optimum for Training Weight and Activation Quantized Networks [4.103701929881022]
  Training deep learning models with low-precision weights and activations involves a demanding optimization task. We show how to overcome the nature of network quantization. We also show numerical evidence of the recurrence phenomenon of weight evolution in training quantized deep networks.
  arXiv  Detail & Related papers  (2020-12-10T09:14:43Z)
• Robust Pruning at Initialization [61.30574156442608]
  A growing need for smaller, energy-efficient, neural networks to be able to use machine learning applications on devices with limited computational resources. For Deep NNs, such procedures remain unsatisfactory as the resulting pruned networks can be difficult to train and, for instance, they do not prevent one layer from being fully pruned.
  arXiv  Detail & Related papers  (2020-02-19T17:09:50Z)

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.