Search Results for author:
Found 6 papers, 1 papers with code
Corrected generalized cross-validation for finite ensembles of penalized estimators
We provide a non-asymptotic analysis of the CGCV and the two intermediate risk estimators for ensembles of convex penalized estimators under Gaussian features and a linear response model.
Out-of-sample error estimate for robust M-estimators with convex penalty
The out-of-sample error estimate enjoys a relative error of order $n^{-1/2}$ in a linear model with Gaussian covariates and independent noise, either non-asymptotically when $p/n\le \gamma$ or asymptotically in the high-dimensional asymptotic regime $p/n\to\gamma'\in(0,\infty)$.
First order expansion of convex regularized estimators
Such first order expansion implies that the risk of $\hat{\beta}$ is asymptotically the same as the risk of $\eta$ which leads to a precise characterization of the MSE of $\hat\beta$; this characterization takes a particularly simple form for isotropic design.
The cost-free nature of optimally tuning Tikhonov regularizers and other ordered smoothers
Our theory reveals that if the Tikhonov regularizers share the same penalty matrix with different tuning parameters, a convex procedure based on $Q$-aggregation achieves the mean square error of the best estimator, up to a small error term no larger than $C\sigma^2$, where $\sigma^2$ is the noise level and $C>0$ is an absolute constant.
De-Biasing The Lasso With Degrees-of-Freedom Adjustment
This modification takes the form of a degrees-of-freedom adjustment that accounts for the dimension of the model selected by Lasso.
On the prediction loss of the lasso in the partially labeled setting
In this paper we revisit the risk bounds of the lasso estimator in the context of transductive and semi-supervised learning.
