基于路径的渐进推理（PaPI）用于节能持续学习
Pathway-based Progressive Inference (PaPI) for Energy-Efficient Continual Learning
AI总结：
本文提出基于路径的渐进推理（PaPI）框架，通过能量约束优化和路径路由机制，在持续学习中实现节能并防止灾难性遗忘，理论上优于EWC和GEM。
摘要：
持续学习系统面临双重挑战：在防止灾难性遗忘的同时保持能源效率，尤其是在资源受限的环境中。本文介绍了基于路径的渐进推理（PaPI），一种新颖的理论框架，通过数学上严谨的路径选择和适应方法来解决这些挑战。我们将持续学习表述为一个能量约束的优化问题，并为我们的路径路由机制提供了正式的收敛保证。我们的理论分析表明，与单片架构相比，PaPI在稳定性-可塑性权衡上实现了$\mathcal{O}(K)$的改进，其中$K$是路径数量。我们使用Fisher信息矩阵分析推导了遗忘率的紧界，并证明了PaPI的能耗与活动参数的数量成正比，而非总模型大小。比较理论分析表明，PaPI比弹性权重巩固（EWC）提供了更强的抗灾难性遗忘保证，同时比EWC和梯度情景记忆（GEM）保持更好的能源效率。我们的实验验证在多个基准上确认了这些理论优势，证明了PaPI在能量受限环境中进行持续学习的有效性。我们的代码可在https://github.com/zser092/PAPI_FILES获取。
英文摘要：
Continual learning systems face the dual challenge of preventing catastrophic forgetting while maintaining energy efficiency, particularly in resource-constrained environments. This paper introduces Pathway-based Progressive Inference (PaPI), a novel theoretical framework that addresses these challenges through a mathematically rigorous approach to pathway selection and adaptation. We formulate continual learning as an energy-constrained optimization problem and provide formal convergence guarantees for our pathway routing mechanisms. Our theoretical analysis demonstrates that PaPI achieves an $\mathcal{O}(K)$ improvement in the stability-plasticity trade-off compared to monolithic architectures, where $K$ is the number of pathways. We derive tight bounds on forgetting rates using Fisher Information Matrix analysis and prove that PaPI's energy consumption scales with the number of active parameters rather than the total model size. Comparative theoretical analysis shows that PaPI provides stronger guarantees against catastrophic forgetting than Elastic Weight Consolidation (EWC) while maintaining better energy efficiency than both EWC and Gradient Episodic Memory (GEM). Our experimental validation confirms these theoretical advantages across multiple benchmarks, demonstrating PaPI's effectiveness for continual learning in energy-constrained settings. Our codes are available at https://github.com/zser092/PAPI_FILES.
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。
