Identifiability of a dissipative knowledge-dynamics model: exact recovery under designed excitation, degeneration on observational data
作者: Arman Kostanian, Armen Beklaryan
分类: cs.LG, math.OC, stat.ML
发布日期: 2026-10-07
💡 一句话要点
提出非线性耗散系统模型以解决人类学习参数可识别性问题
🎯 匹配领域: 支柱九:具身大模型 (Embodied Foundation Models)
关键词: 人类学习 耗散动力学 参数恢复 结构可识别性 教育技术 认知科学 数值求解
📋 核心要点
- 现有方法在从观察数据中恢复学习过程的参数时面临挑战,尤其是在缺乏设计激励的情况下。
- 本文提出了一种基于非线性耗散系统的模型,利用结构可识别性定理在特定条件下实现参数的精确恢复。
- 实验结果显示,在合成数据上参数恢复达到机器精度,但在真实数据上表现不佳,揭示了模型的局限性。
📝 摘要(中文)
人类学习被建模为一种耗散动力学过程,通过实践积累掌握,通过遗忘衰减,并在相互依赖的概念间传播。本文提出了一种非线性耗散系统的常微分方程模型,研究在特定激励条件下如何从数据中恢复模型参数。我们证明了结构可识别性定理,并为两概念情况提供了闭式恢复方案,同时展示了单调性、鲁棒性和L稳定性结果。通过数值方法,我们实现了在大规模学习者群体中进行有效参数估计的可能性。实证研究表明,在理论激励条件下,合成恢复达到机器精度,但在大规模观察基准中未能实现。
🔬 方法详解
问题定义:本文旨在解决如何从观察数据中恢复人类学习过程的参数,现有方法在缺乏设计激励时难以实现精确恢复。
核心思路:通过构建非线性耗散系统的常微分方程模型,论文提出在特定激励条件下实现参数的精确恢复,强调参数的机械意义。
技术框架:整体架构包括参数建模、结构可识别性定理的证明、数值求解方案的设计,以及在合成和真实数据上的验证。主要模块包括概念转移矩阵、遗忘率和实践响应增益的建模。
关键创新:最重要的创新在于证明了在特定激励条件下的结构可识别性,并提供了闭式恢复方案,显著提升了参数恢复的效率与准确性。
关键设计:关键参数包括概念转移矩阵和遗忘率的设置,损失函数设计为最小化预测误差,采用半隐式L稳定方案进行数值求解。
🖼️ 关键图片
📊 实验亮点
实验结果显示,在合成数据上参数恢复达到机器精度,且在大规模学习者群体中实现了比传统方法快两个数量级的估计速度。尽管在真实数据上表现不佳,但遗忘率与主题难度的相关性达到0.83,显示出模型的潜力。
🎯 应用场景
该研究的潜在应用领域包括教育技术、个性化学习系统和认知科学等。通过精确建模人类学习过程,可以为学习者提供更有效的学习策略和反馈,推动教育领域的创新与发展。
📄 摘要(原文)
Human learning is a dissipative dynamical process: mastery accumulates through practice, decays through forgetting, and propagates across interdependent concepts. We model it as a nonlinear dissipative system of ordinary differential equations whose parameters are mechanistically meaningful (a concept-transfer matrix encoding prerequisite coupling, per-concept forgetting rates, and a saturating practice-response gain), and we study when those parameters can actually be recovered from data. We prove a structural identifiability theorem for the associated inverse problem under explicit excitation conditions, with constructive closed-form recovery for the two-concept case, together with monotonicity, robustness and L-stability results. We derive a semi-implicit L-stable scheme for the dissipative subsystem and a batched solver numerically equivalent to the per-trajectory formulation (bit-exact predictions, gradients to $10^{-10}$) yet two orders of magnitude faster, making estimation feasible on cohorts of $10^5$ learners. The empirical study is two-sided. Under the theorem's excitation conditions, synthetic recovery is exact: parameters to machine precision, prerequisite structure at $F_1 = 1.0$. On large observational benchmarks it is not. An apparently strong recovery, with forgetting rates correlating with topic difficulty at Spearman $ρ= 0.83$, is refuted by four independent controls: it survives destroying the temporal order of the data, is matched by a classical Bayesian baseline, and is unaffected by removing real timestamps. We trace this to the stationary structure of the model and show that it is the degeneration the theorem predicts in the absence of designed excitation. The result delineates a sharp boundary between identifiable and unidentifiable regimes and yields a validation protocol for interpretability claims.