通过近邻解耦实现无需遗忘的任务切换
Task Switching Without Forgetting via Proximal Decoupling
AI总结：
本文提出通过操作符分裂分离任务学习与稳定性维持，提升持续学习的稳定性和适应性，无需使用回放缓冲区、贝叶斯采样或元学习组件。
摘要：
在持续学习中，主要挑战是学习新信息而不遗忘旧知识。常见解决方案通过正则化处理这一权衡，惩罚对先前任务关键的参数变化。通常情况下，此正则项直接加到训练损失中并用标准梯度下降优化，将学习与保留信号融合为单一更新，未明确分离关键参数与冗余参数。随着任务序列增长，这种耦合可能过度约束模型，限制前向迁移并导致容量使用效率低下。本文提出一种不同方法，通过操作符分裂分离任务学习与稳定性维持。学习步骤专注于最小化当前任务损失，而近邻稳定性步骤应用稀疏正则化器修剪冗余参数并保留任务相关参数。这将稳定性-可塑性转化为两个互补操作符之间的协商更新，而非冲突梯度。我们为持续学习目标提供了分裂方法的理论依据，并证明所提出求解器在标准基准上取得最佳结果，提升稳定性与适应性，无需回放缓冲区、贝叶斯采样或元学习组件。
英文摘要：
In continual learning, the primary challenge is to learn new information without forgetting old knowledge. A common solution addresses this trade-off through regularization, penalizing changes to parameters critical for previous tasks. In most cases, this regularization term is directly added to the training loss and optimized with standard gradient descent, which blends learning and retention signals into a single update and does not explicitly separate essential parameters from redundant ones. As task sequences grow, this coupling can over-constrain the model, limiting forward transfer and leading to inefficient use of capacity. We propose a different approach that separates task learning from stability enforcement via operator splitting. The learning step focuses on minimizing the current task loss, while a proximal stability step applies a sparse regularizer to prune unnecessary parameters and preserve task-relevant ones. This turns the stability-plasticity into a negotiated update between two complementary operators, rather than a conflicting gradient. We provide theoretical justification for the splitting method on the continual-learning objective, and demonstrate that our proposed solver achieves state-of-the-art results on standard benchmarks, improving both stability and adaptability without the need for replay buffers, Bayesian sampling, or meta-learning components.
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。
