Convergence guarantees for kernel-based quadrature rules in misspecified settings
원문 초록
Kernel-based quadrature rules are becoming important in machine learning and statistics, as they achieve super-$\sqrt{n}$ convergence rates in numerical integration, and thus provide alternatives to Monte Carlo integration in challenging settings where integrands are expensive to evaluate or where integrands are high dimensional. These rules are based on the assumption that the integrand has a certain degree of smoothness, which is expressed as that the integrand belongs to a certain reproducing kernel Hilbert space (RKHS). However, this assumption can be violated in practice (e.g., when the integrand is a black box function), and no general theory has been established for the convergence of kernel quadratures in such misspecified settings. Our contribution is in proving that kernel quadratures can be consistent even when the integrand does not belong to the assumed RKHS, i.e., when the integrand is less smooth than assumed. Specifically, we derive convergence rates that depend on the (unknown) lesser smoothness of the integrand, where the degree of smoothness is expressed via powers of RKHSs or via Sobolev spaces.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
How Far Are We from Optimal Reasoning Efficiency?
A Dictionary of Closed-Form Kernel Mean Embeddings
Force-Free Molecular Dynamics Through Autoregressive Equivariant Networks
Underdamped Diffusion Bridges with Applications to Sampling
Provable Quantum Algorithm Advantage for Gaussian Process Quadrature
FNIN: A Fourier Neural Operator-based Numerical Integration Network for Surface-form-gradients
토론
이 논문과 연결된 포럼 글이 아직 없습니다.