Finite-sample analysis of M-estimators using self-concordance - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2020

Finite-sample analysis of M-estimators using self-concordance


The classical asymptotic theory for parametric $M$-estimators guarantees that, in the limit of infinite sample size, the excess risk has a chi-square type distribution, even in the misspecified case. We demonstrate how self-concordance of the loss allows to characterize the critical sample size sufficient to guarantee a chi-square type in-probability bound for the excess risk. Specifically, we consider two classes of losses: (i) self-concordant losses in the classical sense of Nesterov and Nemirovski, i.e., whose third derivative is uniformly bounded with the $3/2$ power of the second derivative; (ii) pseudo self-concordant losses, for which the power is removed. These classes contain losses corresponding to several generalized linear models, including the logistic loss and pseudo-Huber losses. Our basic result under minimal assumptions bounds the critical sample size by $O(d \cdot d_{\text{eff}}),$ where $d$ the parameter dimension and $d_{\text{eff}}$ the effective dimension that accounts for model misspecification. In contrast to the existing results, we only impose local assumptions that concern the population risk minimizer $\theta_*$. Namely, we assume that the calibrated design, i.e., design scaled by the square root of the second derivative of the loss, is subgaussian at $\theta_*$. Besides, for type-ii losses we require boundedness of a certain measure of curvature of the population risk at $\theta_*$. Our improved result bounds the critical sample size from above as $O(\max\{d_{\text{eff}}, d \log d\})$ under slightly stronger assumptions. Namely, the local assumptions must hold in the neighborhood of $\theta_*$ given by the Dikin ellipsoid of the population risk. Interestingly, we find that, for logistic regression with Gaussian design, there is no actual restriction of conditions: the subgaussian parameter and curvature measure remain near-constant over the Dikin ellipsoid. Finally, we extend some of these results to $\ell_1$-penalized estimators in high dimensions.
Fichier principal
Vignette du fichier
main-self-concordant.pdf (1.69 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-01895127 , version 1 (14-10-2018)
hal-01895127 , version 2 (15-11-2020)
hal-01895127 , version 3 (30-11-2020)



Dmitrii M. Ostrovskii, Francis Bach. Finite-sample analysis of M-estimators using self-concordance. 2020. ⟨hal-01895127v3⟩
3197 View
257 Download



Gmail Mastodon Facebook X LinkedIn More