Optimal signal estimation using cross-validation
Robert D. Nowak · IEEE Signal Processing Letters · 1997
This letter develops an optimal, nonlinear estimator of a deterministic signal in noise. The methods of penalized least-squares and cross-validation (CV) balance the bias-variance tradeoff and lead to a closed form expression for the estimator. The estimator is simultaneously optimal in a "small-sample", predictive sum of squares sense and asymptotically optimal in the mean square sense.