Methods for reasoning under uncertainty are a key building block of accurate and reliable machine learning systems. Bayesian methods provide a general framework to quantify uncertainty. However, because of model misspecification and the use of approximate inference, Bayesian uncertainty estimates are often inaccurate -- for example, a 90% credible interval may not contain the true outcome 90% of the time. Here, we propose a simple procedure for calibrating any regression algorithm; when applied to Bayesian and probabilistic models, it is guaranteed to produce calibrated uncertainty estimates given enough data. Our procedure is inspired by Platt scaling and extends previous work on classification. We evaluate this approach on Bayesian linear regression, feedforward, and recurrent neural networks, and find that it consistently outputs well-calibrated credible intervals while improving performance on time series forecasting and model-based reinforcement learning tasks.

本文探讨贝叶斯方法在不确定性问题上的推理方法，提出一种简单有效的校准程序，可以保证在足够的数据下，任何回归算法都能够产生准确的校准不确定性估计，并应用于贝叶斯线性回归、前向和递归神经网络中，能够稳定输出准确的区间预测，并提高时间序列预测和基于模型的强化学习性能。

使用校准回归的深度学习准确不确定性