Layerwise Proximal Replay: A Proximal Point Method for Online Continual Learning
CoRR(2024)
摘要
In online continual learning, a neural network incrementally learns from a
non-i.i.d. data stream. Nearly all online continual learning methods employ
experience replay to simultaneously prevent catastrophic forgetting and
underfitting on past data. Our work demonstrates a limitation of this approach:
networks trained with experience replay tend to have unstable optimization
trajectories, impeding their overall accuracy. Surprisingly, these
instabilities persist even when the replay buffer stores all previous training
examples, suggesting that this issue is orthogonal to catastrophic forgetting.
We minimize these instabilities through a simple modification of the
optimization geometry. Our solution, Layerwise Proximal Replay (LPR), balances
learning from new and replay data while only allowing for gradual changes in
the hidden activation of past data. We demonstrate that LPR consistently
improves replay-based online continual learning methods across multiple problem
settings, regardless of the amount of available replay memory.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要