This performs a brute-force grid search with uniform sampling over the unit hypercube with increasing granularity. (Your target function should scale the candidate vectors as necessary to cover the desired space.) This grid-search increases the granularity after each pass, and carefully avoids sampling anywhere that it has sampled before.
|
| GGridSearch (GTargetFunction *pCritic) |
|
virtual | ~GGridSearch () |
|
virtual const GVec & | currentVector () |
| Returns the best vector yet found. More...
|
|
virtual double | iterate () |
| Each pass will complete after ((2^n)+1)^d iterations. The distance between samples at that point will be 1/(2^n). After it completes n=30, it will begin repeating. 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...
|
|