发表机构
Idaho National Laboratory; U.S. Department of Energy（爱达荷国家实验室; 美国能源部）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对训练数据缺失的机器学习问题，从动力系统视角推导了具有李雅普诺夫稳定性的自适应学习机制，在多模态场景中验证了其能提升学习一致性与稳定性的效果。
AI 中文摘要
训练期间数据缺失时，机器学习模型应学习什么？我们从动力系统视角审视学习过程，将数据缺失视为一种结构化的驱动损失，该损失限制了参数误差动力学的可控性，最终推导得到具有李雅普诺夫稳定性特性的自适应机制，该机制可调节模型更新，以在部分、间歇性可观测性下保持学习一致性。在循环激励下，我们的分析提供了关于损失残差与预处理更新几何之间有界闭环失配的ISS型残差到状态界。我们在多模态场景中评估了这种定向可观测性感知自适应学习方法的有效性，强化了其在甚至是病态稀疏领域和问题中也能促进学习一致性与稳定性的前提。
英文摘要
What should a machine learning model learn when data is missing during training? We look at the learning process from a dynamical systems perspective, cast data missingness as a structured loss of actuation that limits controllability of the parameter error dynamics, and ultimately derive adaptation mechanisms with Lyapunov stability characteristics that throttle model updates in ways that preserve learning coherence under partial, intermittent observability. Under recurrent excitation, our analysis provides ISS-type residual-to-state bounds with respect to a bounded closed-loop mismatch between the loss residual and the preconditioned update geometry. We evaluate the efficacy of our directional observability-aware adaptive learning approach on multimodal contexts, reinforcing its premise in promoting learning coherence and stability even in pathologically sparse domains and problems.
