Opened 7 years ago
Last modified 3 years ago
#2882 assigned enhancement
Deserialization of RegressionModels triggers a recalcuatlion of estimated values — at Version 1
| Reported by: | pfleck | Owned by: | |
|---|---|---|---|
| Priority: | medium | Milestone: | HeuristicLab 3.3.17 |
| Component: | Problems.DataAnalysis | Version: | |
| Keywords: | Cc: |
Description (last modified by mkommend)
On deserializing a gradient boosted tree solution, the GBTSurrogateModel recaltulates the actual GBTModel even if the model is not yet used - which can be quite runtime expensive. The same issue applies to all regression models.
Instead, the model should only be created when the model is actually needed to estimate values.
Change History (1)
comment:1 Changed 7 years ago by mkommend
- Component changed from Algorithms.DataAnalysis to Problems.DataAnalysis
- Description modified (diff)
- Priority changed from medium to high
- Summary changed from Create GBT-model lazily after deserialization to Deserialization of RegressionModels triggers a recalcuatlion of estimated values
- Type changed from enhancement to defect
Note: See
TracTickets for help on using
tickets.
