Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning
Yarin Gal Zoubin Ghahramani University of Cambridge
Abstract
Deep learning tools have gained tremendous attention in applied machine learning. However such tools for regression and classification do not capture model uncertainty. In comparison, Bayesian models offer a mathematically grounded framework to reason about model uncertainty, but usually come with a prohibitive computational cost. In this paper we develop a new theoretical framework casting dropout training in deep neural networks (NNs) as approximate Bayesian inference in deep Gaussian processes. A direct result of this theory gives us tools to model uncertainty with dropout NNs – extracting information from existing models that has been thrown away so far. This mitigates the problem of representing uncertainty in deep learning without sacrificing either computational complexity or test accuracy. We perform an extensive study of the properties of dropout’s uncertainty. Various network architectures and non-linearities are assessed on tasks of regression and classification, using MNIST as an example. We show a considerable improvement in predictive log-likelihood and RMSE compared to existing state-of-the-art methods, and finish by using dropout’s uncertainty in deep reinforcement
中文速览
用神经网络（neural network）做预测时，模型往往给不出可靠的不确定性估计——即便预测概率很高，也可能是"自信但错误"的结果。这篇论文从理论上证明，在深度神经网络中使用 Dropout（随机丢弃神经元）等价于对一类被称为深度高斯过程（deep Gaussian process）的概率模型做近似贝叶斯推断（approximate Bayesian inference），由此推导出一套利用 Dropout 提取模型不确定性的方法：测试时只需对同一输入做多次随机前向传播，用输出的均值和方差即可估计预测的置信程度，无需改动网络结构或增加训练开销。实验表明，该方法在回归和分类任务上的预测对数似然与均方根误差均优于现有最先进方法，在深度强化学习中也展现出实用价值。这项工作的意义在于，仅凭已有的 Dropout 网络就能"免费"获得数学上有据可查的不确定性估计，填补了深度学习在可靠性评估上的重要空白。
原文 arXiv:1506.02142;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1506.02142v6