Weight Uncertainty in Neural Networks, Charles Blundell, Julien Cornebise, Koray Kavukcuoglu, and Daan Wierstra, 2015Proceedings of the 32nd International Conference on Machine Learning (ICML), Vol. 37 (PMLR) - 介绍了Bayes by Backprop,一种广泛用于训练贝叶斯神经网络的变分推断方法,详细阐述了ELBO目标函数和重参数化技巧。
Stochastic Gradient Hamiltonian Monte Carlo, Tianqi Chen, Emily Fox, Carlos Guestrin, 2014Proceedings of the 31st International Conference on Machine Learning, Vol. 32 (PMLR) - 介绍了随机梯度哈密顿蒙特卡洛(SGHMC),这是一种使用小批量梯度训练贝叶斯神经网络的关键MCMC算法,如本节所述。
On Calibration of Modern Neural Networks, Chuan Guo, Geoff Pleiss, Yu Sun, Kilian Q. Weinberger, 2017Proceedings of the 34th International Conference on Machine Learning, Vol. 70 (PMLR) - 研究了现代神经网络中的校准问题,并介绍了可靠性图,为评估贝叶斯神经网络的概率预测质量提供了背景信息。