Shorting Dynamics and Structured Kernel Regularization
Fuente:
arXiv
Salvato in:
| Autore principale: | |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908694182100992 |
|---|---|
| author | Tian, James |
| author_facet | Tian, James |
| contents | This paper develops a nonlinear operator dynamic that progressively removes the influence of a prescribed feature subspace while retaining maximal structure elsewhere. The induced sequence of positive operators is monotone, admits an exact residual decomposition, and converges to the classical shorted operator. Transporting this dynamic to reproducing kernel Hilbert spaces yields a corresponding family of kernels that converges to the largest kernel dominated by the original one and annihilating the given subspace. In the finite-sample setting, the associated Gram operators inherit a structured residual decomposition that leads to a canonical form of kernel ridge regression and a principled way to enforce nuisance invariance. This gives a unified operator-analytic approach to invariant kernel construction and structured regularization in data analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_04874 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Shorting Dynamics and Structured Kernel Regularization Tian, James Functional Analysis Machine Learning Primary: 47N30, Secondary: 46E22, 47B65, 62J07, 68T05 This paper develops a nonlinear operator dynamic that progressively removes the influence of a prescribed feature subspace while retaining maximal structure elsewhere. The induced sequence of positive operators is monotone, admits an exact residual decomposition, and converges to the classical shorted operator. Transporting this dynamic to reproducing kernel Hilbert spaces yields a corresponding family of kernels that converges to the largest kernel dominated by the original one and annihilating the given subspace. In the finite-sample setting, the associated Gram operators inherit a structured residual decomposition that leads to a canonical form of kernel ridge regression and a principled way to enforce nuisance invariance. This gives a unified operator-analytic approach to invariant kernel construction and structured regularization in data analysis. |
| title | Shorting Dynamics and Structured Kernel Regularization |
| topic | Functional Analysis Machine Learning Primary: 47N30, Secondary: 46E22, 47B65, 62J07, 68T05 |
| url | https://arxiv.org/abs/2512.04874 |