From e302a61e3043f0a0f5f36e65e9b404a4b0835a14 Mon Sep 17 00:00:00 2001 From: Davis King Date: Sat, 25 Nov 2017 09:57:33 -0500 Subject: [PATCH] Clarified spec --- dlib/global_optimization/find_max_global_abstract.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/dlib/global_optimization/find_max_global_abstract.h b/dlib/global_optimization/find_max_global_abstract.h index ef4f718ba..1246b5ae2 100644 --- a/dlib/global_optimization/find_max_global_abstract.h +++ b/dlib/global_optimization/find_max_global_abstract.h @@ -114,7 +114,11 @@ namespace dlib elsewhere rather than on further improving the current local optima found so far. That is, once a local maxima is identified to about solver_epsilon accuracy, the algorithm will spend all its time exploring the functions to - find other local maxima to investigate. + find other local maxima to investigate. An epsilon of 0 means it will keep + solving until it reaches full floating point precision. Larger values will + cause it to switch to pure global exploration sooner and therefore might be + more effective if your objective function has many local maxima and you don't + care about a super high precision solution. - find_max_global() runs until one of the following is true: - The total number of calls to the provided functions is == num.max_calls - More than max_runtime time has elapsed since the start of this function. @@ -178,7 +182,11 @@ namespace dlib elsewhere rather than on further improving the current local optima found so far. That is, once a local maxima is identified to about solver_epsilon accuracy, the algorithm will spend all its time exploring the function to - find other local maxima to investigate. + find other local maxima to investigate. An epsilon of 0 means it will keep + solving until it reaches full floating point precision. Larger values will + cause it to switch to pure global exploration sooner and therefore might be + more effective if your objective function has many local maxima and you don't + care about a super high precision solution. - find_max_global() runs until one of the following is true: - The total number of calls to f() is == num.max_calls - More than max_runtime time has elapsed since the start of this function.