Sequential Bayesian inference can be used for continual learning to prevent catastrophic forgetting of past tasks and provide an informative prior when learning new tasks. We revisit sequential Bayesian inference and test whether having access to the true posterior is guaranteed to prevent catastrophic forgetting in Bayesian neural networks. To do this we perform sequential Bayesian inference using Hamiltonian Monte Carlo. We propagate the posterior as a prior for new tasks by fitting a density estimator on Hamiltonian Monte Carlo samples. We find that this approach fails to prevent catastrophic forgetting demonstrating the difficulty in performing sequential Bayesian inference in neural networks. From there we study simple analytical examples of sequential Bayesian inference and CL and highlight the issue of model misspecification which can lead to sub-optimal continual learning performance despite exact inference. Furthermore, we discuss how task data imbalances can cause forgetting. From these limitations, we argue that we need probabilistic models of the continual learning generative process rather than relying on sequential Bayesian inference over Bayesian neural network weights. In this vein, we also propose a simple baseline called Prototypical Bayesian Continual Learning, which is competitive with state-of-the-art Bayesian continual learning methods on class incremental continual learning vision benchmarks.
翻译:连续的贝耶斯推论,并测试能否保证在巴伊西亚神经网络中获取真实的远地点,以防止灾难性的遗忘。要做到这一点,我们使用汉密尔顿·蒙特卡洛进行连续的巴伊斯推论。我们通过在汉密尔顿·蒙特卡洛样本上安装一个密度测量仪,宣传后台作为新任务的前台。我们发现,这一方法无法防止灾难性地忘记在神经网络中出现连续的巴伊斯推断的困难。我们从那里研究接连的巴伊斯推断和CL的简单分析例子,并突出模型的错误区分问题,这可能导致在精确的推论下出现亚非最佳的持续学习表现。此外,我们讨论任务数据不平衡如何导致忘记。我们从这些局限性中认为,我们需要持续学习的基因化过程的概率模型,而不是依靠连续的贝伊斯测距对贝伊斯神经网络重量的推论。我们从中研究连续的Bayeservical-cal-cle releglement on the laversal-stal asimal relegal-clegress on the lavial-stal-stal-stal-stal