Erratum: SGDQN is Less Careful than Expected

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.

• Type: Journal
• Year: 2010
• Where: JMLR
• Authors: Antoine Bordes, Léon Bottou, Patrick Gallinari, Jonathan Chang, S. Alex Smith
• Keywords: Flawed Sgd-qn Algorithm, JMLR 2010, Scale Learning Challenge, SGD-QN Algorithm