Gaussian Process Regression with Mismatched Models
| dc.creator | Sollich, Peter | |
| dc.date | 2001-06-22 | |
| dc.date.accessioned | 2026-07-07T02:41:53Z | |
| dc.date.available | 2026-07-07T02:41:53Z | |
| dc.description | Learning curves for Gaussian process regression are well understood when the `student' model happens to match the `teacher' (true data generation process). I derive approximations to the learning curves for the more generic case of mismatched models, and find very rich behaviour: For large input space dimensionality, where the results become exact, there are universal (student-independent) plateaux in the learning curve, with transitions in between that can exhibit arbitrarily many over-fitting maxima. In lower dimensions, plateaux also appear, and the asymptotic decay of the learning curve becomes strongly student-dependent. All predictions are confirmed by simulations. | |
| dc.description | 7 pages, style file nips01e.sty included | |
| dc.identifier | https://arxiv.org/abs/cond-mat/0106475 | |
| dc.identifier | http://arxiv.org/abs/cond-mat/0106475 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/17920 | |
| dc.subject | Disordered Systems and Neural Networks | |
| dc.subject | Statistical Mechanics | |
| dc.title | Gaussian Process Regression with Mismatched Models | |
| dc.type | text |