arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2011.12829stat.MLcs.LG
收藏

你所需要的只是贝叶斯深度学习的良好函数先验

All You Need is a Good Functional Prior for Bayesian Deep Learning

EURECOM(欧洲通信学院)

Ba-Hien Tran, Simone Rossi, Dimitrios Milios, Maurizio Filippone

摘要:

贝叶斯神经网络的处理规定了一个先验分布,指定其权重和偏置参数。这带来了一个挑战,因为现代神经网络的特点是大量的参数,这些先验的选择有一个不受控制的影响,诱导功能的先验,这是通过采样的参数,从他们的先验分布获得的函数的分布。我们认为这是贝叶斯深度学习的一个巨大限制,这项工作以一种实用有效的方式解决了这一限制。我们的建议是根据更容易引出的功能先验进行推理,并以反映这种功能先验的方式“调整”神经网络参数的先验。高斯过程提供了一个严格的框架来定义函数的先验分布,我们提出了一个新的和强大的框架,以匹配他们的先验与神经网络的功能先验的基础上最小化他们的瓦瑟斯坦距离。我们提供了大量的实验证据,将这些先验与可扩展的马尔可夫链蒙特卡罗采样相结合,与先验的替代选择和最先进的近似贝叶斯深度学习方法相比,提供了系统性的大性能改进。我们认为这项工作是朝着实现神经网络(包括卷积神经网络)的完全贝叶斯处理这一长期挑战的方向迈出的重要一步。

英文摘要:

The Bayesian treatment of neural networks dictates that a prior distribution is specified over their weight and bias parameters. This poses a challenge because modern neural networks are characterized by a large number of parameters, and the choice of these priors has an uncontrolled effect on the induced functional prior, which is the distribution of the functions obtained by sampling the parameters from their prior distribution. We argue that this is a hugely limiting aspect of Bayesian deep learning, and this work tackles this limitation in a practical and effective way. Our proposal is to reason in terms of functional priors, which are easier to elicit, and to "tune" the priors of neural network parameters in a way that they reflect such functional priors. Gaussian processes offer a rigorous framework to define prior distributions over functions, and we propose a novel and robust framework to match their prior with the functional prior of neural networks based on the minimization of their Wasserstein distance. We provide vast experimental evidence that coupling these priors with scalable Markov chain Monte Carlo sampling offers systematically large performance improvements over alternative choices of priors and state-of-the-art approximate Bayesian deep learning approaches. We consider this work a considerable step in the direction of making the long-standing challenge of carrying out a fully Bayesian treatment of neural networks, including convolutional neural networks, a concrete possibility.

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。

↑