This is a hill climber for semi-linear error surfaces that minimizes testing with an approach like binary-search. It only searches approximately within the unit cube (although it may stray a little outside of it). It is the target function's responsibility to map this into an appropriate space.
|
| | GMinBinSearch (GTargetFunction *pCritic) |
| |
| virtual | ~GMinBinSearch () |
| |
| virtual const GVec & | currentVector () |
| | Returns the best vector yet found. More...
|
| |
| virtual double | iterate () |
| | Try another random vector. More...
|
| |
| | GOptimizer (GTargetFunction *pCritic) |
| |
| virtual | ~GOptimizer () |
| |
| void | basicTest (double minAccuracy, double warnRange=0.001) |
| | This is a helper method used by the unit tests of several model learners. More...
|
| |
| double | searchUntil (size_t nBurnInIterations, size_t nIterations, double dImprovement) |
| | This will first call iterate() nBurnInIterations times, then it will repeatedly call iterate() in blocks of nIterations times. If the error heuristic has not improved by the specified ratio after a block of iterations, it will stop. (For example, if the error before the block of iterations was 50, and the error after is 49, then training will stop if dImprovement is > 0.02.) If the error heuristic is not stable, then the value of nIterations should be large. More...
|
| |
Public Member Functions inherited from GClasses::GOptimizer