提出新框架缓解持续学习中的灾难性遗忘，理论与实证结合效果接近顶尖水平。
Path-Coordinated Continual Learning with Neural Tangent Kernel-Justified Plasticity: A Theoretical Framework with Near State-of-the-Art Performance
- 基于神经正切核理论设计可塑性约束，协调学习路径。
- 在Split-CIFAR10上实现66.7%平均准确率，遗忘率仅23.4%。
- 揭示条件数>10^11为学习能力临界点，适合研究持续学习机制者。
灾难性遗忘是持续学习的核心挑战，神经网络在学习新任务时会遗忘旧任务。本文提出一种新的路径协调式持续学习框架，融合神经正切核（NTK）理论的合理可塑性约束、威尔逊置信区间统计验证及多指标路径质量评估。实验显示，在Split-CIFAR10上平均准确率达66.7%，灾难性遗忘率仅为23.4%，显著优于基线且接近当前最先进水平。进一步发现，NTK条件数超过10^11时存在学习能力临界点。该策略随任务序列推进遗忘率从27%降至18%，体现系统稳定性。80%的发现路径经严格统计验证，中间任务保留率维持在90%-97%。分析确定了持续学习环境的核心容量限制，并提供了增强自适应正则化的实用建议。
原文摘要 · Abstract (English)
Catastrophic forgetting is one of the fundamental issues of continual learning because neural networks forget the tasks learned previously when trained on new tasks. The proposed framework is a new path-coordinated framework of continual learning that unites the Neural Tangent Kernel (NTK) theory of principled plasticity bounds, statistical validation by Wilson confidence intervals, and evaluation of path quality by the use of multiple metrics. Experimental evaluation shows an average accuracy of 66.7% at the cost of 23.4% catastrophic forgetting on Split-CIFAR10, a huge improvement over the baseline and competitive performance achieved, which is very close to state-of-the-art results. Further, it is found out that NTK condition numbers are predictive indicators of learning capacity limits, showing the existence of a critical threshold at condition number $>10^{11}$. It is interesting to note that the proposed strategy shows a tendency of lowering forgetting as the sequence of tasks progresses (27% to 18%), which is a system stabilization. The framework validates 80% of discovered paths with a rigorous statistical guarantee and maintains 90-97% retention on intermediate tasks. The core capacity limits of the continual learning environment are determined in the analysis, and actionable insights to enhance the adaptive regularization are offered.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。