Opened 22 months ago
Closed 20 months ago
#2782 closed feature request (done)
Gaussian process regression should also calculate the leave-one-out predictive probability
Reported by: | gkronber | Owned by: | gkronber |
---|---|---|---|
Priority: | medium | Milestone: | HeuristicLab 3.3.15 |
Component: | Algorithms.DataAnalysis | Version: | 3.3.14 |
Keywords: | Cc: |
Description
Change History (13)
comment:1 Changed 22 months ago by gkronber
comment:2 Changed 22 months ago by gkronber
r14918: removed a comment
comment:3 Changed 21 months ago by gkronber
- Owner set to gkronber
- Status changed from new to accepted
comment:4 Changed 21 months ago by gkronber
- Owner changed from gkronber to mkommend
- Status changed from accepted to reviewing
comment:5 follow-up: ↓ 6 Changed 20 months ago by mkommend
- Owner changed from mkommend to gkronber
- Status changed from reviewing to readytorelease
comment:6 in reply to: ↑ 5 Changed 20 months ago by gkronber
Replying to mkommend:
Reviewed and tested r14899 and r14918.
I haven't verified that the calculation matches exactly in GPML. <BR> During testing i noticed that the LOO pred probability (which is not a probability btw) is rather large (1E40 or more) for models with little variance on the estimates.
Thanks for the review. I also noticed that the resulting values are rather strange. I need to re-check this. The GPML book calls this value either 'LOO log predictive probability' or alternatively 'log pseudo-likelihood'.
EDIT: the calculation has been checked and fixed. See comment:8 and comment:9
comment:7 Changed 20 months ago by gkronber
r15160: renamed LOO log predictive probability to LooCvNegativeLogPseudoLikelihood
comment:8 Changed 20 months ago by gkronber
Compared results for LOO calculation to the results of the GPML package using the following MATLAB script. The results are completely off.
trainX = towerDatascaled(1:500,1:25); trainY = towerDatascaled(1:500,26); hyp.mean = [0]; hyp.cov = [0; 0]; hyp.lik = [-3]; hyp2 = minimize(hyp, @gp, -100, @infGaussLik, 'meanConst', 'covSEiso', 'likGauss', trainX, trainY); [ymu, ys2, fmu, fs2, lp] = gp(hyp2, 'infLOO', 'meanConst', 'covSEiso', 'likGauss', trainX, trainY, trainX, trainY); sum_lp = sum(lp);
r15163: changed calculation of LOO log pseudo likelihood (evaluation order) which seemingly improves the results. More testing is necessary.
comment:9 Changed 20 months ago by gkronber
r15165: fixed calculation of log pseudo-likelihood by adding the noise term to the covariance function.
ki[i] += sqrSigmaNoise;
Several other changes have been made which are effectively only re-arrangements of the formula.
The new calculation has been checked using the MATLAB GPML package for meanConst and covSEiso. The results are the same.
comment:10 Changed 20 months ago by gkronber
r15187: renamed remaining fields and properties referring to 'PredictiveProbability'
comment:11 Changed 20 months ago by gkronber
comment:12 Changed 20 months ago by gkronber
all changesets merged to stable
comment:13 Changed 20 months ago by gkronber
- Resolution set to done
- Status changed from readytorelease to closed
r14899: implemented calculation of LOO predictive probability for Gaussian process regression