无散度线性化神经网络:积分表示与最优逼近率
Divergence-free Linearized Neural Networks: Integral Representation and Optimal Approximation Rates
AI总结:
本文通过线性化ReLU^k神经网络的积分表示理论,结合稳定势提升,推导出无散度Sobolev向量场的最优逼近率,并在二维和三维空间中验证了理论速率及精确无散度条件的有效性。
摘要:
本文研究了通过线性化浅层神经网络(也称随机特征模型或有限神经元空间)近似无散度向量场的数值方法,结合稳定势提升与ReLU^k网络的标量Sobolev积分表示理论,推导出无散度Sobolev向量场的积分表示并通过近似参数的准均匀分布论证,得到满足精确无散度约束的线性化ReLU^k神经网络的最优逼近率。数值实验在二维和三维空间中,包括L^2投影和稳态Stokes问题,验证了理论速率并展示了精确无散度条件在计算中的有效性。
英文摘要:
This paper studies the numerical approximation of divergence-free vector fields by linearized shallow neural networks, also referred to as random feature models or finite neuron spaces. Combining the stable potential lifting for divergence-free fields with the scalar Sobolev integral representation theory via ReLU$^k$ networks, we derive a core integral representation of divergence-free Sobolev vector fields through antisymmetric potentials parameterized by linearized ReLU$^k$ neural networks. This representation, together with a quasi-uniform distribution argument for the inner parameters, yields optimal approximation rates for such linearized ReLU$^k$ neural networks under an exact divergence-free constraint. Numerical experiments in two and three spatial dimensions, including $L^2$ projection and steady Stokes problems, confirm the theoretical rates and illustrate the effectiveness of exactly divergence-free conditions in computation.
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。