Continual Learning via Sequential Function-Space Variational Inference
This work addresses the problem of continual learning for AI systems that need to adapt to new tasks without forgetting old ones, representing an incremental improvement over existing methods.
The paper tackles the challenge of applying sequential Bayesian inference to neural networks for continual learning by proposing an optimization objective based on sequential function-space variational inference, which improves predictive accuracy and reduces reliance on stored data from previous tasks.
Sequential Bayesian inference over predictive functions is a natural framework for continual learning from streams of data. However, applying it to neural networks has proved challenging in practice. Addressing the drawbacks of existing techniques, we propose an optimization objective derived by formulating continual learning as sequential function-space variational inference. In contrast to existing methods that regularize neural network parameters directly, this objective allows parameters to vary widely during training, enabling better adaptation to new tasks. Compared to objectives that directly regularize neural network predictions, the proposed objective allows for more flexible variational distributions and more effective regularization. We demonstrate that, across a range of task sequences, neural networks trained via sequential function-space variational inference achieve better predictive accuracy than networks trained with related methods while depending less on maintaining a set of representative points from previous tasks.