An Adaptive Empirical Bayesian Method for Sparse Deep Learning

Authors: Wei Deng, Xiao Zhang, Faming Liang, Guang Lin
Published: 2019-10-23 | Updated: 2020-04-13

Source: https://arxiv.org/abs/1910.10791

PDF: https://arxiv.org/pdf/1910.10791

Labels Predicted by AI

最適化戦略 収束保証 深層学習技術

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

We propose a novel adaptive empirical Bayesian method for sparse deep learning, where the sparsity is ensured via a class of self-adaptive spike-and-slab priors. The proposed method works by alternatively sampling from an adaptive hierarchical posterior distribution using stochastic gradient Markov Chain Monte Carlo (MCMC) and smoothly optimizing the hyperparameters using stochastic approximation (SA). We further prove the convergence of the proposed method to the asymptotically correct distribution under mild conditions. Empirical applications of the proposed method lead to the state-of-the-art performance on MNIST and Fashion MNIST with shallow convolutional neural networks and the state-of-the-art compression performance on CIFAR10 with Residual Networks. The proposed method also improves resistance to adversarial attacks.