Differences

This shows you the differences between two versions of the page.

--- papers:bordes-bottou-gallinari-2009 [2010/12/28 11:06]
leonb
+++ papers:bordes-bottou-gallinari-2009 [2017/11/29 10:27] (current)
leonb [Errata]
@@ Line 12: / Line 12: @@
 PASCAL Large Scale Learning Challenge.
-//Erratum//:
+<html><font color=blue></html>
-Please see section [[#Erratum]] below.
+//Errata//:
+Please see section [[#Errata]] below.
+<html></font></html>
 <box 99% orange>
@@ Line 54: / Line 56: @@
-==== Erratum ====
+==== Errata ====
 The SGDQN algorithm as described in this paper contains a subtle flaw
 described in a subsequent [[:papers:bordes-2010|erratum]].
+There is a missing 1/2 factor in the bounds of theorem 1.
+\[
+ \def\w{\mathbf{w}}
+ {\frac{1}{2}} \frac{{\mathrm tr}(\mathbf{HBGB})}{2\lambda_{\max}-1}\,t^{-1} + {\mathrm o}(t^{-1})
+  ~\leq~ \mathbb{E}_{\sigma}\big[\:{\cal P}_n(\w_t)-{\cal P}_n(\w^*_n)\:\big] ~\leq~
+  {\frac{1}{2}} \frac{{\mathrm tr}(\mathbf{HBGB})}{2\lambda_{\min}-1}\,t^{-1} + {\mathrm o}(t^{-1})
+\]
+The version of the paper found on this site contains the correct theorem and proof.