Seminar by Joseph Salmon on Thursday, Octobre 18

Joseph Salmon (Duke University) will give a talk on Thursday, Octobre 18 at 1:30 P.M.  in room  DB312 (Dareau buiding).
Titre: Optimal aggregation of affine estimators

Abstract: We consider the problem of
combining a (possibly uncountably infinite) set of affine estimators
in non-parametric regression model with heteroscedastic Gaussian
noise. Focusing on the exponentially weighted aggregate, we prove a
PAC-Bayesian type inequality that leads to sharp oracle inequalities
in discrete but also in continuous settings. The framework is general
enough to cover the combinations of various procedures such as least
square regression, kernel ridge regression, shrinking estimators and
many other estimators used in the literature on statistical inverse
problems. This is a joint work with Arnak Dalalyan.

Comments are closed.