Newshot

Learning Curves and Prediction Persistence to Under-Regularization of Spectral Algorithms in Large Dimensions

Summary

arXiv:2604.23212v2 Announce Type: replace Abstract: We study how prediction risk changes as regularization is reduced for spectral algorithms when the sample size $n$ and dimension $d$ satisfy $n\asymp d^\gamma$ for fixed $\gamma>0$. For inner-product kernels on the sphere, under a source condition with smoothness $s\geq0$ and a signal nondegeneracy condition, we characterize the conditional excess risk up to constant factors at each fixed admissible scale $\lambda\asymp d^{-u}$, $u>0$, and at interpolation. The resulting risk orders describe the effects of source smoothness, filter qualification, and transitions between spectral blocks. They identify when the conditional excess risk retains the minimax risk order as regularization is weakened from an optimal scale to interpolation, and when an interval before interpolation exhibits a polynomially larger risk. We also compare the kernel risk with a population sequence risk for the same spectral filter, using a deterministic regularizat…

Original text(via arXiv stat.ML)

Statistics > Machine Learning

Title:Learning Curves and Prediction Persistence to Under-Regularization of Spectral Algorithms in Large Dimensions

Abstract:We study how prediction risk changes as regularization is reduced for spectral algorithms when the sample size $n$ and dimension $d$ satisfy $n\asymp d^\gamma$ for fixed $\gamma>0$. For inner-product kernels on the sphere, under a source condition with smoothness $s\geq0$ and a signal nondegeneracy condition, we characterize the conditional excess risk up to constant factors at each fixed admissible scale $\lambda\asymp d^{-u}$, $u>0$, and at interpolation. The resulting risk orders describe the effects of source smoothness, filter qualification, and transitions between spectral blocks. They identify when the conditional excess risk retains the minimax risk order as regularization is weakened from an optimal scale to interpolation, and when an interval before interpolation exhibits a polynomially larger risk. We also compare the kernel risk with a population sequence risk for the same spectral filter, using a deterministic regularization scale bounded below by order $n^{-1}$. Finally, for noninteger $\gamma$, we extend the risk characterization for kernel ridge regression to kernels on general domains under spectral scaling, hyper-contractivity, and tail diagonal concentration conditions, together with the source and signal conditions.
Subjects:Machine Learning (stat.ML) ; Machine Learning (cs.LG); Statistics Theory (math.ST)
Cite as:arXiv:2604.23212 [stat.ML]
(or arXiv:2604.23212v2 [stat.ML] for this version)
https://doi.org/10.48550/arXiv.2604.23212 arXiv-issued DOI via DataCite

Submission history

Access Paper:

  • HTML (experimental)

Current browse context:

References & Citations

  • Google Scholar
  • Semantic Scholar

BibTeX formatted citation

Bookmark

Bibliographic and Citation Tools

Code, Data and Media Associated with this Article

Demos

Recommenders and Search Tools

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

The text above was extracted automatically from the source page and may miss images, tables or code blocks. The original is authoritative.

Published by arXiv stat.ML
This site only summarises and aggregates; copyright stays with the original author. Headlines and summaries follow the source — where they differ, the original wins.
Read the original ↗