3 problems

Effective-dimension conjecture. The relevant sample complexity for the second kernel ridge regression fit is governed by $d_{\mathrm{eff}}$. This prediction is motivated by an anal…

Let $\hat{f}^{(aug)}$ and $\hat{f}^{(adv)}$ denote the augmented and adversarial estimators, respectively, and let the coefficients of the $k$-th order expansion of the kernel feat…

Let (F)SBL denote the sparse Bayesian learning algorithms discussed in the study, and let squared error and marginal likelihood be their respective prediction and optimization crit…