Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-off

• URL: http://arxiv.org/abs/2211.16667v3
• Date: Mon, 24 Apr 2023 04:24:07 GMT
• Title: Dynamic Sparse Training via Balancing the Exploration-Exploitation Trade-off
• Authors: Shaoyi Huang, Bowen Lei, Dongkuan Xu, Hongwu Peng, Yue Sun, Mimi Xie, Caiwen Ding
• Abstract summary: Sparse training could significantly mitigate the training costs by reducing the model size. Existing sparse training methods mainly use either random-based or greedy-based drop-and-grow strategies. In this work, we consider the dynamic sparse training as a sparse connectivity search problem. Experimental results show that sparse models (up to 98% sparsity) obtained by our proposed method outperform the SOTA sparse training methods.
• Score: 19.230329532065635
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Over-parameterization of deep neural networks (DNNs) has shown high prediction accuracy for many applications. Although effective, the large number of parameters hinders its popularity on resource-limited devices and has an outsize environmental impact. Sparse training (using a fixed number of nonzero weights in each iteration) could significantly mitigate the training costs by reducing the model size. However, existing sparse training methods mainly use either random-based or greedy-based drop-and-grow strategies, resulting in local minimal and low accuracy. In this work, we consider the dynamic sparse training as a sparse connectivity search problem and design an exploitation and exploration acquisition function to escape from local optima and saddle points. We further design an acquisition function and provide the theoretical guarantees for the proposed method and clarify its convergence property. Experimental results show that sparse models (up to 98\% sparsity) obtained by our proposed method outperform the SOTA sparse training methods on a wide variety of deep learning tasks. On VGG-19 / CIFAR-100, ResNet-50 / CIFAR-10, ResNet-50 / CIFAR-100, our method has even higher accuracy than dense models. On ResNet-50 / ImageNet, the proposed method has up to 8.2\% accuracy improvement compared to SOTA sparse training methods.

Related papers

• Just How Flexible are Neural Networks in Practice? [89.80474583606242]
  It is widely believed that a neural network can fit a training set containing at least as many samples as it has parameters. In practice, however, we only find solutions via our training procedure, including the gradient and regularizers, limiting flexibility.
  arXiv  Detail & Related papers  (2024-06-17T12:24:45Z)
• Accurate Neural Network Pruning Requires Rethinking Sparse Optimization [87.90654868505518]
  We show the impact of high sparsity on model training using the standard computer vision and natural language processing sparsity benchmarks. We provide new approaches for mitigating this issue for both sparse pre-training of vision models and sparse fine-tuning of language models.
  arXiv  Detail & Related papers  (2023-08-03T21:49:14Z)
• AUTOSPARSE: Towards Automated Sparse Training of Deep Neural Networks [2.6742343015805083]
  We propose Gradient Annealing (GA) to explore the non-uniform distribution of sparsity inherent within neural networks. GA provides an elegant trade-off between sparsity and accuracy without the need for additional sparsity-inducing regularization. We integrate GA with the latest learnable pruning methods to create an automated sparse training algorithm called AutoSparse.
  arXiv  Detail & Related papers  (2023-04-14T06:19:07Z)
• Two Heads are Better than One: Robust Learning Meets Multi-branch Models [14.72099568017039]
  We propose Branch Orthogonality adveRsarial Training (BORT) to obtain state-of-the-art performance with solely the original dataset for adversarial training. We evaluate our approach on CIFAR-10, CIFAR-100, and SVHN against ell_infty norm-bounded perturbations of size epsilon = 8/255, respectively.
  arXiv  Detail & Related papers  (2022-08-17T05:42:59Z)
• Controlled Sparsity via Constrained Optimization or: How I Learned to Stop Tuning Penalties and Love Constraints [81.46143788046892]
  We focus on the task of controlling the level of sparsity when performing sparse learning. Existing methods based on sparsity-inducing penalties involve expensive trial-and-error tuning of the penalty factor. We propose a constrained formulation where sparsification is guided by the training objective and the desired sparsity target in an end-to-end fashion.
  arXiv  Detail & Related papers  (2022-08-08T21:24:20Z)
• Structured Directional Pruning via Perturbation Orthogonal Projection [13.704348351073147]
  A more reasonable approach is to find a sparse minimizer along the flat minimum valley found byNIST. We propose the structured directional pruning based on projecting the perturbations onto the flat minimum valley. Experiments show that our method obtains the state-of-the-art pruned accuracy (i.e. 93.97% on VGG16, CIFAR-10 task) without retraining.
  arXiv  Detail & Related papers  (2021-07-12T11:35:47Z)
• Effective Model Sparsification by Scheduled Grow-and-Prune Methods [73.03533268740605]
  We propose a novel scheduled grow-and-prune (GaP) methodology without pre-training the dense models. Experiments have shown that such models can match or beat the quality of highly optimized dense models at 80% sparsity on a variety of tasks.
  arXiv  Detail & Related papers  (2021-06-18T01:03:13Z)
• A Simple Fine-tuning Is All You Need: Towards Robust Deep Learning Via Adversarial Fine-tuning [90.44219200633286]
  We propose a simple yet very effective adversarial fine-tuning approach based on a $textitslow start, fast decay$ learning rate scheduling strategy. Experimental results show that the proposed adversarial fine-tuning approach outperforms the state-of-the-art methods on CIFAR-10, CIFAR-100 and ImageNet datasets.
  arXiv  Detail & Related papers  (2020-12-25T20:50:15Z)
• Training Sparse Neural Networks using Compressed Sensing [13.84396596420605]
  We develop and test a novel method based on compressed sensing which combines the pruning and training into a single step. Specifically, we utilize an adaptively weighted $ell1$ penalty on the weights during training, which we combine with a generalization of the regularized dual averaging (RDA) algorithm in order to train sparse neural networks.
  arXiv  Detail & Related papers  (2020-08-21T19:35:54Z)
• Extrapolation for Large-batch Training in Deep Learning [72.61259487233214]
  We show that a host of variations can be covered in a unified framework that we propose. We prove the convergence of this novel scheme and rigorously evaluate its empirical performance on ResNet, LSTM, and Transformer.
  arXiv  Detail & Related papers  (2020-06-10T08:22:41Z)

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.