← 研踪 PaperTrailarXiv:2604.23212 · v2
Learning Curves and Prediction Persistence to Under-Regularization of Spectral Algorithms in Large Dimensions
首次提交 2026-04-25 16:38
版本更新 2026-11-19 09:29
雷达观测 2026-11-20 10:50
摘要
We study how prediction risk changes as regularization is reduced for spectral algorithms when the sample size and dimension satisfy for fixed . For inner-product kernels on the sphere, under a source condition with smoothness and a signal nondegeneracy condition, we characterize the conditional excess risk up to constant factors at each fixed admissible scale , , 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 . Finally, for noninteger , 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.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-19 09:29 · 最新观测版本
Learning Curves and Prediction Persistence to Under-Regularization of Spectral Algorithms in Large Dimensions
We study how prediction risk changes as regularization is reduced for spectral algorithms when the sample size and dimension satisfy for fixed . For inner-product kernels on the sphere, under a source condition with smoothness and a signal nondegeneracy condition, we characterize the conditional excess risk up to constant factors at each fixed admissible scale , , 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 . Finally, for noninteger , 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.
查看此版本解读 →查看此版本原文 ↗