Opened 7 years ago
Last modified 6 years ago
#2722 assigned feature request
Evaluator for symbolic regression models for learning a variance model
Reported by: | gkronber | Owned by: | gkronber |
---|---|---|---|
Priority: | low | Milestone: | HeuristicLab 4.x Backlog |
Component: | Problems.DataAnalysis.Symbolic.Regression | Version: | |
Keywords: | Cc: |
Description
Change History (12)
comment:1 Changed 7 years ago by gkronber
- Status changed from new to accepted
comment:2 Changed 7 years ago by gkronber
comment:3 Changed 7 years ago by gkronber
- Owner changed from gkronber to mkommend
- Status changed from accepted to reviewing
comment:4 Changed 7 years ago by gkronber
Linear scaling needs to be turned off.
comment:5 Changed 7 years ago by gkronber
The objective is to maximize the following log likelihood that the observed residuals stem from a zero-mean normal distribution with std. dev. s = f(x).
var l2pi = Math.Log(2.0 * Math.PI); var ll = -0.5 * boundedEstimatedValues.Zip(targetValues, (s, t) => +l2pi + Math.Log(s * s) + (t * t) / (s * s) ).Sum(); return ll;
This is problematic as the sign of s has no effect on the result (same for the sign of t). It would probably be better to model the variance s^{2} directly. However, in this case negative values for s^{2} are not possible and must be prevented. On option would be to produce a model for log(s^{2}) instead.
comment:6 Changed 7 years ago by gkronber
- Owner changed from mkommend to gkronber
- Status changed from reviewing to assigned
comment:7 Changed 7 years ago by gkronber
- Milestone changed from HeuristicLab 3.3.15 to HeuristicLab 3.3.x Backlog
- Status changed from assigned to accepted
comment:8 Changed 6 years ago by gkronber
- Milestone changed from HeuristicLab 3.3.x Backlog to HeuristicLab 3.3.15
- Status changed from accepted to reviewing
Should either be released or removed from trunk
comment:9 Changed 6 years ago by gkronber
r15198: removed evaluator for learning of variance models from the trunk to prepare for release
comment:10 Changed 6 years ago by gkronber
comment:11 Changed 6 years ago by gkronber
- Milestone changed from HeuristicLab 3.3.15 to HeuristicLab 3.3.x Backlog
- Status changed from reviewing to assigned
comment:12 Changed 6 years ago by gkronber
- Milestone changed from HeuristicLab 3.3.x Backlog to HeuristicLab 4.x Backlog
- Priority changed from medium to low
- Version 3.3.14 deleted
r14528: added an evaluator for symbolic regression models which calculates the likelihood that variable values are sampled from a zero mean Gaussian distribution where the variance is given by the model. This can be used to learn input-dependent variances.