1Blurb::
2(Experimental) How to select new points
3
4Description::
5\c adaptive_sampling is an experimental capability that is not ready
6for production use at this time.
7
8With batch or multi-point selection, the true model can be evaluated
9in parallel and thus increase throughput before refitting our
10surrogate model. This proposes a new challenge as the problem of
11choosing a single point and choosing multiple points off a surrogate
12are fundamentally different. Selecting the \c n best scoring
13candidates is more than likely to generate a set of points clustered
14in one area which will not be conducive to adapting the surrogate.
15
16We have implemented several strategies for batch selection of points.
17These are described in the User's manual and are the subject of
18active research.
19
20The \c batch_selection strategies include:
21<ol>
22<li> \c naive:
23<li> \c distance_penalty
24<li> \c constant_liar
25<li> \c topology
26</ol>
27
28Topics::
29Examples::
30Theory::
31Faq::
32See_Also::
33