A concentration inequality for the excess risk in least-squares regression with random design and heteroscedastic noise
arXiv:1702.05063
Abstract
We prove a new and general concentration inequality for the excess risk in least-squares regression with random design and heteroscedastic noise. No specific structure is required on the model, except the existence of a suitable function that controls the local suprema of the empirical process. So far, only the case of linear contrast estimation was tackled in the literature with this level of generality on the model. We solve here the case of a quadratic contrast, by separating the behavior of a linearized empirical process and the empirical process driven by the squares of functions of models.
References in corpus (7)
- Simultaneous analysis of Lasso and Dantzig selector
- Concentration around the mean for maxima of empirical processes
- Data-driven calibration of penalties for least-squares regression
- A new perspective on least squares under convex constraint
- Choice of V for V-Fold Cross-Validation in Least-Squares Density Estimation
- V-fold cross-validation improved: V-fold penalization
- Towards the study of least squares estimators with convex penalty