Skip to yearly menu bar Skip to main content


Poster

Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem

Simon Segert

Halle B #161
[ ]
Fri 10 May 7:30 a.m. PDT — 9:30 a.m. PDT

Abstract:

We consider the problem of linear estimation, and establish an extension of the Gauss-Markov theorem, in which the bias operator is allowed to be non-zero but bounded with respect to a matrix norm of Schatten type. We derive simple and explicit formulas for the optimal estimator in the cases of Nuclear and Spectral norms (with the Frobenius case recovering ridge regression). Additionally, we analytically derive the generalization error in multiple random matrix ensembles, and compare with Ridge regression. Finally, we conduct an extensive simulation study, in which we show that the cross-validated Nuclear and Spectral regressors can outperform Ridge in several circumstances.

Chat is not available.