通过霍纳多项式实现参数最小的神经微分方程求解器
Parameter-Minimal Neural DE Solvers via Horner Polynomials
AI总结:
通过霍纳多项式实现参数最小的神经微分方程求解器,在保持低参数量的同时提升求解精度和效率。
摘要:
我们提出了一种参数最小的神经架构,通过将假设空间限制在霍纳因子化多项式中,从而获得一个隐式且可微的试解,仅需少量可学习的系数。初始条件通过构造精确地被强制执行,通过固定低阶多项式自由度,因此训练仅专注于匹配在配点处的微分方程残差。为了在不放弃低参数 regime 的情况下减少近似误差,我们引入了一种分段(类似样条)的扩展,该扩展在子区间上训练多个小型霍纳模型,同时在段边界处强制连续性(和一阶导数连续性)。在示例 ODE 基准和热方程示例中,具有几十(或更少)参数的霍纳网络能够准确匹配解及其导数,并在相同训练设置下优于小型 MLP 和正弦表示基线,展示了资源高效科学建模的实用精度-参数权衡。
英文摘要:
We propose a parameter-minimal neural architecture for solving differential equations by restricting the hypothesis class to Horner-factorized polynomials, yielding an implicit, differentiable trial solution with only a small set of learnable coefficients. Initial conditions are enforced exactly by construction by fixing the low-order polynomial degrees of freedom, so training focuses solely on matching the differential-equation residual at collocation points. To reduce approximation error without abandoning the low-parameter regime, we introduce a piecewise ("spline-like") extension that trains multiple small Horner models on subintervals while enforcing continuity (and first-derivative continuity) at segment boundaries. On illustrative ODE benchmarks and a heat-equation example, Horner networks with tens (or fewer) parameters accurately match the solution and its derivatives and outperform small MLP and sinusoidal-representation baselines under the same training settings, demonstrating a practical accuracy-parameter trade-off for resource-efficient scientific modeling.
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。