信任区域持续学习作为隐式元学习器
Trust Region Continual Learning as an Implicit Meta-Learner
AI总结：
本文提出信任区域持续学习，通过结合生成重放和Fisher度量信任区域约束，实现隐式元学习效果，在任务增量扩散图像生成和持续扩散策略控制中取得最佳性能。
摘要：
持续学习旨在顺序获取任务而不发生灾难性遗忘，但标准策略面临核心权衡：基于正则化的方法（如EWC）在任务最优值弱重叠时可能过度约束更新，而基于重放的方法可以保持性能但因不完美重放而漂移。我们研究了一种混合视角：\emph{信任区域持续学习}，它将生成重放与Fisher度量信任区域约束相结合。我们证明，在局部近似下，得到的更新具有MAML风格的解释，包含一个隐式内步：重放提供旧任务梯度信号（类似查询），而Fisher加权惩罚提供高效的离线曲率塑造（类似支持）。这产生了持续学习中的涌现元学习特性：模型成为初始化，在每次任务转换后快速\emph{重新收敛}到先前任务最优值，而无需显式优化双层目标。实验上，在任务增量扩散图像生成和持续扩散策略控制中，信任区域持续学习实现了最佳最终性能和保留，并且比EWC、重放和持续元学习基线更快地恢复早期任务性能。
英文摘要：
Continual learning aims to acquire tasks sequentially without catastrophic forgetting, yet standard strategies face a core tradeoff: regularization-based methods (e.g., EWC) can overconstrain updates when task optima are weakly overlapping, while replay-based methods can retain performance but drift due to imperfect replay. We study a hybrid perspective: \emph{trust region continual learning} that combines generative replay with a Fisher-metric trust region constraint. We show that, under local approximations, the resulting update admits a MAML-style interpretation with a single implicit inner step: replay supplies an old-task gradient signal (query-like), while the Fisher-weighted penalty provides an efficient offline curvature shaping (support-like). This yields an emergent meta-learning property in continual learning: the model becomes an initialization that rapidly \emph{re-converges} to prior task optima after each task transition, without explicitly optimizing a bilevel objective. Empirically, on task-incremental diffusion image generation and continual diffusion-policy control, trust region continual learning achieves the best final performance and retention, and consistently recovers early-task performance faster than EWC, replay, and continual meta-learning baselines.
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。
