Continual Learning via Sequential Function-Space Variational Inference
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.
Code (1)
Tasks
Bayesian InferenceContinual LearningSequential Bayesian InferenceVariational InferenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Sequential Function-Space Variational Inference via Gaussian Mixture Approximation
Continual learning is learning from a sequence of tasks with the aim of learning new tasks without forgetting old tasks. Sequential function-space variational inference (SFSVI) is a continual learning method based on var…
Continual LearningVariational InferenceContinual Multi-task Gaussian Processes
We address the problem of continual learning in multi-task Gaussian process (GP) models for handling sequential input-output observations. Our approach extends the existing prior-posterior recursion of online Bayesian in…
Bayesian InferenceContinual LearningGaussian ProcessesStochastic Optimization+1Variational Auto-Regressive Gaussian Processes for Continual Learning
Through sequential construction of posteriors on observing data online, Bayes' theorem provides a natural framework for continual learning. We develop Variational Auto-Regressive Gaussian Processes (VAR-GPs), a principle…
Bayesian InferenceContinual LearningGaussian ProcessesRevised Regularization for Efficient Continual Learning through Correlation-Based Parameter Update in Bayesian Neural Networks
We propose a Bayesian neural network-based continual learning algorithm using Variational Inference, aiming to overcome several drawbacks of existing methods. Specifically, in continual learning scenarios, storing networ…
Continual LearningTransfer LearningVariational InferenceVariational Continual Bayesian Meta-Learning
Conventional meta-learning considers a set of tasks from a stationary distribution. In contrast, this paper focuses on a more complex online setting, where tasks arrive sequentially and follow a non-stationary distributi…
Meta-LearningTransfer LearningVariational Inference