Show pageOld revisionsBacklinksBack to top This page is read only. You can view the source, but not change it. Ask your administrator if you think this is wrong. # Approaches for target metric optimization - Optimize another metric, postprocess - Write custom loss function - Any, if you can ## Early stopping - Optimize metric M1, monitor metric M2 - Stop when M2 score is the best ## Conclusion - Loss vs metric - Approaches in general: - Just run the right model - open/approaches-for-target-metric-optimization.txt Last modified: 2024/10/05 06:15by 127.0.0.1