Bayesian neural networks (BNNs) allow us to reason about uncertainty in a principled way. Stochastic Gradient Langevin Dynamics (SGLD) enables efficient BNN learning by drawing samples from the BNN posterior using mini-batches. However, SGLD and its extensions require storage of many copies of the model parameters, a potentially prohibitive cost, especially for large neural networks. We propose a framework, Adversarial Posterior Distillation, to distill the SGLD samples using a Generative Adversarial Network (GAN). At test-time, samples are generated by the GAN. We show that this distillation framework incurs no loss in performance on recent BNN applications including anomaly detection, active learning, and defense against adversarial attacks. By construction, our framework not only distills the Bayesian predictive distribution, but the posterior itself. This allows one to compute quantities such as the approximate model variance, which is useful in downstream tasks. To our knowledge, these are the first results applying MCMC-based BNNs to the aforementioned downstream applications.

提出了对抗后验蒸馏框架，使用生成对抗网络(GAN)来压缩随机梯度 Langevin 动力学 (SGLD) 采样，使其在效率和精度方面都具有优势，能够将 Bayes 神经网络(BNN) 应用于诸如异常检测、主动学习和对抗性攻击防御等细分领域

贝叶斯神经网络后验分布的对抗蒸馏