# Finite-sample Analysis of M-estimators using Self-concordance

16 Oct 2018Dmitrii OstrovskiiFrancis Bach

We demonstrate how self-concordance of the loss can be exploited to obtain asymptotically optimal rates for M-estimators in finite-sample regimes. We consider two classes of losses: (i) canonically self-concordant losses in the sense of Nesterov and Nemirovski (1994), i.e., with the third derivative bounded with the $3/2$ power of the second; (ii) pseudo self-concordant losses, for which the power is removed, as introduced by Bach (2010)... (read more)

PDF Abstract

# Code Add Remove

No code implementations yet. Submit your code now