choose your own randomized regularizer

[Grace Wahba]

.............................
Re: Regularizing fashions...choose your own:

as per Wray Buntine's remarks 
about Scott Markel's discussion of SQP 

Also Re: `Large problems require stochastic methods' -Yann Le Cun 

Variants of the fast randomized version of Generalized 
Cross Validation might be implementable with very large 
optimization problems...SQL? see 
	
	AUTHOR = {D. Girard},
        TITLE = {A Fast `{M}onte-{C}arlo Cross-Validation' Procedure for Large
 Least Squares Problems with Noisy Data},
        JOURNAL = {Numer. Math.},
        YEAR = {1989},
        VOLUME = {56},
	PAGES = {1-23}
        
        AUTHOR = {D. Girard},
        TITLE = {Asymptotic optimality of the fast randomized versions 
	of {GCV} and ${C}_{L}$ in ridge regression and regularization },
        JOURNAL = {Ann. Statist.},
	YEAR = {1991},
        VOLUME = {19},
        PAGES = {1950-1963}