Non-Asymptotic Variational Learning for Monotone Nonlinear Multiscale Elliptic Equations: Scale-Robust Primal-Dual Bounds and Strong-Form Statistical Ill-Conditioning

arXiv:2607.15702v2 Announce Type: replace-cross Abstract: We develop a non-asymptotic approximation, sampling, and finite-iteration optimization theory for variational physics-informed approximation of uniformly monotone nonlinear multiscale elliptic equations. For boundary-compatible neural feature classes, the population error splits into approximation, empirical quadrature, and projected-gradient terms, with all non-approximation constants uniform in the microscopic scale (arepsilon). Assuming a quantitative corrected (H^1)-estimate, a two-scale state class yields [ mathcal A_m^arepsilon le Cigl(arepsilon+Phi_{0,m_0}^2+Phi_{1,m_1}^2igr) ] in arbitrary dimension. We further introduce a convex primal-dual physics loss whose population value is a computable upper certificate for the state error. With additional flux-corrector regularity, a divergence-compatible two-scale flux class gives a certified state-flux bound combining (O(arepsilon)) approximation, state and flux feature errors, empirical sampling error, and an (O(K^{-1})) optimization term. In contrast, for general periodic nonlinear fluxes satisfying a natural nondegeneracy condition, the empirical Rademacher complexities of strong-residual and squared-residual classes are bounded below by constant multiples of ((arepsilonsqrt N)^{-1}) and ((arepsilon^2sqrt N)^{-1}), respectively. These optimizer-independent lower bounds hold in every spatial dimension. Numerical experiments confirm the predicted (arepsilon)- and (N)-scalings for nonlinear fluxes in (d=1,2,3), validate every computed primal-dual certificate, and show that corrector-enriched classes substantially reduce energy and (H^1) errors as the microscopic scale is refined.

Source: arXiv cs.LG | 2026-07-23