Commit 90af783b authored by Davis King's avatar Davis King

Made the spec more clear

--HG--
extra : convert_revision : svn%3Afdd8eb12-d10e-0410-9acb-85c331704f74/trunk%403535
parent 4aef8a35
...@@ -56,8 +56,9 @@ namespace dlib ...@@ -56,8 +56,9 @@ namespace dlib
requires requires
- This function is called by the OCA optimizer each iteration. - This function is called by the OCA optimizer each iteration.
- current_objective_value == the current value of the objective function f(w) - current_objective_value == the current value of the objective function f(w)
- current_error_gap == the bound on how much lower the objective function - current_error_gap == The bound on how much lower the objective function
can drop before we reach the optimal point can drop before we reach the optimal point. At the optimal solution the
error gap is equal to 0.
- num_cutting_planes == the number of cutting planes the algorithm is currently - num_cutting_planes == the number of cutting planes the algorithm is currently
using using
- num_iterations == A count of the total number of iterations that have executed - num_iterations == A count of the total number of iterations that have executed
...@@ -97,7 +98,7 @@ namespace dlib ...@@ -97,7 +98,7 @@ namespace dlib
- #risk_value == R(#current_solution) - #risk_value == R(#current_solution)
- #risk_subgradient == an element of the subgradient of R() at the - #risk_subgradient == an element of the subgradient of R() at the
point #current_solution point #current_solution
- Note that risk_value and risk_subgradient are NOT multiplied by get_c() - Note that #risk_value and #risk_subgradient are NOT multiplied by get_c()
!*/ !*/
}; };
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment