Erratum: Sgdqn is less careful than expected
Résumé
The SGD-QN algorithm described in Bordes et al. (2009) contains a subtle flaw that prevents it from reaching its design goals. Yet the flawed SGD-QN algorithm has worked well enough to be a winner of the first Pascal Large Scale Learning Challenge (Sonnenburg et al., 2008). This document clarifies the situation, proposes a corrected algorithm, and evaluates its performance.
Domaines
Apprentissage [cs.LG]
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Loading...