Neural network pruning is a highly effective technique aimed at reducing the computational and memory demands of large neural networks. In this research paper, we present a novel approach to pruning neural networks utilizing Bayesian inference, which can seamlessly integrate into the training procedure. Our proposed method leverages the posterior probabilities of the neural network prior to and following pruning, enabling the calculation of Bayes factors. The calculated Bayes factors guide the iterative pruning. Through comprehensive evaluations conducted on multiple benchmarks, we demonstrate that our method achieves desired levels of sparsity while maintaining competitive accuracy.

翻译：神经网络剪枝是一种旨在降低大型神经网络计算与内存需求的高效技术。本研究提出了一种利用贝叶斯推断进行神经网络剪枝的新方法，该方法可无缝集成至训练流程中。我们提出的方法利用了剪枝前后神经网络的后验概率，从而能够计算贝叶斯因子。计算所得的贝叶斯因子指导了迭代剪枝过程。通过在多个基准数据集上的全面评估，我们证明了该方法在保持竞争性精度的同时，能够达到所需的稀疏性水平。