arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.11994stat.MLcs.LG
收藏

神经网络的Gauss-Newton方法与近似推理的解纠缠

Disentangling the Gauss-Newton Method and Approximate Inference for Neural Networks

École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院);RIKEN Center for Advanced Intelligence Project(理化学研究所高级智能中心);EPFL School of Computer and Communication Sciences(洛桑联邦理工学院计算机与通信科学学院)

Alexander Immer

摘要:

在这篇论文中,我们解开了贝叶斯深度学习的广义高斯-牛顿和近似推理。广义高斯-牛顿方法是一种优化方法,用于几种流行的贝叶斯深度学习算法。将高斯-牛顿方法与拉普拉斯和高斯变分近似相结合的算法最近在贝叶斯深度学习中取得了最先进的成果。虽然拉普拉斯和高斯变分近似已经被广泛研究,但它们与高斯-牛顿方法的相互作用仍然不清楚。最近对贝叶斯深度学习中先验和后验近似的批评进一步敦促人们需要更深入地理解实用算法。对神经网络的高斯-牛顿法、拉普拉斯和高斯变分逼近的个别分析提供了理论见解和新的实用算法。我们发现,高斯-牛顿方法简化了潜在的概率模型显着。特别地,高斯-牛顿方法与近似推断的组合可以被转换为线性或高斯过程模型中的推断。拉普拉斯和高斯变分近似可以随后提供这些简化模型的后验近似。这种对最近贝叶斯深度学习算法的新的解开的理解也导致了新的方法:首先,与高斯过程的连接使新的函数空间推理算法成为可能。其次,我们提出了一个边际似然近似的底层概率模型来调整神经网络超参数。最后,确定的基础模型导致不同的方法来计算预测分布。事实上,我们发现贝叶斯神经网络的这些预测方法通常比默认选择更好,并且解决了拉普拉斯近似的一个常见问题。

英文摘要:

In this thesis, we disentangle the generalized Gauss-Newton and approximate inference for Bayesian deep learning. The generalized Gauss-Newton method is an optimization method that is used in several popular Bayesian deep learning algorithms. Algorithms that combine the Gauss-Newton method with the Laplace and Gaussian variational approximation have recently led to state-of-the-art results in Bayesian deep learning. While the Laplace and Gaussian variational approximation have been studied extensively, their interplay with the Gauss-Newton method remains unclear. Recent criticism of priors and posterior approximations in Bayesian deep learning further urges the need for a deeper understanding of practical algorithms. The individual analysis of the Gauss-Newton method and Laplace and Gaussian variational approximations for neural networks provides both theoretical insight and new practical algorithms. We find that the Gauss-Newton method simplifies the underlying probabilistic model significantly. In particular, the combination of the Gauss-Newton method with approximate inference can be cast as inference in a linear or Gaussian process model. The Laplace and Gaussian variational approximation can subsequently provide a posterior approximation to these simplified models. This new disentangled understanding of recent Bayesian deep learning algorithms also leads to new methods: first, the connection to Gaussian processes enables new function-space inference algorithms. Second, we present a marginal likelihood approximation of the underlying probabilistic model to tune neural network hyperparameters. Finally, the identified underlying models lead to different methods to compute predictive distributions. In fact, we find that these prediction methods for Bayesian neural networks often work better than the default choice and solve a common issue with the Laplace approximation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑