论持续学习中的序贯贝叶斯推断
On Sequential Bayesian Inference for Continual Learning
AI总结：
本文研究序贯贝叶斯推断能否防止神经网络灾难性遗忘，通过 HMC 与密度估计实验及解析分析揭示模型误设和数据不平衡问题，并提出具有竞争力的 Prototypical Bayesian Continual Learning 基线。
摘要：
序贯贝叶斯推断可用于持续学习，以防止对过去任务的灾难性遗忘，并在学习新任务时提供信息丰富的先验。我们重新审视序贯贝叶斯推断，并检验在贝叶斯神经网络中，获得真实后验是否能保证防止灾难性遗忘。为此，我们使用 Hamiltonian Monte Carlo 执行序贯贝叶斯推断。通过在 Hamiltonian Monte Carlo 样本上拟合密度估计器，我们将后验作为新任务的先验进行传播。我们发现该方法未能防止灾难性遗忘，这表明在神经网络中执行序贯贝叶斯推断存在困难。在此基础上，我们研究了序贯贝叶斯推断与持续学习的简单解析示例，并强调模型误设问题：即使推断精确，模型误设仍可能导致次优的持续学习性能。此外，我们讨论了任务数据不平衡如何引发遗忘。基于这些局限，我们认为需要对持续学习生成过程建立概率模型，而不是依赖贝叶斯神经网络权重上的序贯贝叶斯推断。沿此思路，我们还提出了一个名为 Prototypical Bayesian Continual Learning 的简单基线；在类别增量持续学习视觉基准上，该方法与最先进的贝叶斯持续学习方法具有竞争力。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
