From a6c35a8d748df8fa1e27c3a0bb527ea1513fd555 Mon Sep 17 00:00:00 2001 From: Maarten Keijzer Date: Tue, 29 Dec 2015 15:28:43 +0100 Subject: [PATCH] Updated the documentation for 'gradient' and 'Hessian' (subscript error) --- doc/model.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/doc/model.md b/doc/model.md index dd92cf6dc..ee6a604fd 100644 --- a/doc/model.md +++ b/doc/model.md @@ -150,8 +150,8 @@ Obj^{(t)} = \sum_{i=1}^n [l(y_i, \hat{y}_i^{(t-1)}) + g_i f_t(x_i) + \frac{1}{2} where the ``$g_i$`` and ``$h_i$`` are defined as ```math -g_i &= \partial_{\hat{y}_i^{(t)}} l(y_i, \hat{y}_i^{(t-1)})\\ -h_i &= \partial_{\hat{y}_i^{(t)}}^2 l(y_i, \hat{y}_i^{(t-1)}) +g_i &= \partial_{\hat{y}_i^{(t-1)}} l(y_i, \hat{y}_i^{(t-1)})\\ +h_i &= \partial_{\hat{y}_i^{(t-1)}}^2 l(y_i, \hat{y}_i^{(t-1)}) ``` After we remove all the constants, the specific objective at step ``$t$`` becomes