Abstract:It is often possible to perform reduced order modelling by specifying linear subspace which accurately captures the dynamics of the system. This approach becomes especially appealing when linear subspace explicitly depends on parameters of the problem. A practical way to apply such a scheme is to compute subspaces for a selected set of parameters in the computationally demanding offline stage and in the online stage approximate subspace for unknown parameters by interpolation. For realistic problems the space of parameters is high dimensional, which renders classical interpolation strategies infeasible or unreliable. We propose to relax the interpolation problem to regression, introduce several loss functions suitable for subspace data, and use a neural network as an approximation to high-dimensional target function. To further simplify a learning problem we introduce redundancy: in place of predicting subspace of a given dimension we predict larger subspace. We show theoretically that this strategy decreases the complexity of the mapping for elliptic eigenproblems with constant coefficients and makes the mapping smoother for general smooth function on the Grassmann manifold. Empirical results also show that accuracy significantly improves when larger-than-required subspaces are predicted. With the set of numerical illustrations we demonstrate that subspace regression can be useful for a range of tasks including parametric eigenproblems, deflation techniques, relaxation methods, optimal control and solution of parametric partial differential equations.
| Comments: | Accepted to ICLR 2026, reviewed at this https URL |
| Subjects: | Machine Learning (cs.LG); Numerical Analysis (math.NA) |
| Cite as: | arXiv:2509.23249 [cs.LG] |
| (or arXiv:2509.23249v4 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2509.23249 arXiv-issued DOI via DataCite |
From: Vladimir Fanaskov [view email]
[v1]
Sat, 27 Sep 2025 10:56:03 UTC (3,552 KB)
[v2]
Wed, 1 Oct 2025 12:37:24 UTC (3,552 KB)
[v3]
Fri, 27 Feb 2026 15:05:32 UTC (3,660 KB)
[v4]
Thu, 16 Apr 2026 06:05:17 UTC (3,661 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。