A new concentration inequality for the excess risk in least-squares regression with random design and heteroscedastic noise
share
We prove a new concentration inequality for the excess risk of a M-estimator in least-squares regression with random design and heteroscedastic noise. This kind of result is a central tool in modern model selection theory, as well as in recent achievements concerning the behavior of regularized estimators such as LASSO, group LASSO and SLOPE.
READ FULL TEXT