On Sequential Bayesian Inference for Continual Learning

Abstract

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.

Supercedes Entropy publication with updates to Section 4

References in corpus (17)

• Overcoming catastrophic forgetting in neural networks
• Prototypical Networks for Few-shot Learning
• A continual learning survey: Defying forgetting in classification tasks
• Neural Tangent Kernel: Convergence and Generalization in Neural Networks
• Continual Learning Through Synaptic Intelligence
• Progress & Compress: A scalable framework for continual learning
• Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
• What Are Bayesian Neural Network Posteriors Really Like?
• Continual Deep Learning by Functional Regularisation of Memorable Past
• Optimal Continual Learning has Perfect Memory and is NP-hard
• Uncertainty-guided Continual Learning with Bayesian Neural Networks
• Scaling Hamiltonian Monte Carlo Inference for Bayesian Neural Networks with Symmetric Splitting
• Measuring and regularizing networks in function space
• Hierarchical Indian Buffet Neural Networks for Bayesian Continual Learning
• Continual Learning using a Bayesian Nonparametric Dictionary of Weight Factors
• Continual Learning via Sequential Function-Space Variational Inference
• Variational Auto-Regressive Gaussian Processes for Continual Learning

Cited by in corpus (1)

• Continual Learning and Catastrophic Forgetting