Kvíz spojený s průvodcem · Střední úroveň
Huberova ztráta a robustní regresní kvíz
Porovnejte Huberovy dvě oblasti ztrát s metodami nejmenších čtverců a konsenzuálními metodami a procvičte si přiřazování robustních odhadů k datovým podmínkám.
Otázka 1 z 8
Jak Huberova ztráta zachází s reziduum daleko za svým prahem?
Náhled každé otázky8 otázky
Odpovědi a vysvětlení se zobrazují, jak budete v kvízu.
- Jak Huberova ztráta zachází s reziduum daleko za svým prahem?
- Its penalty grows linearly with residual magnitude
- Its penalty becomes exactly zero
- It squares the residual at a faster rate
- It removes the observation automatically
- Jaké chování používá Huberova ztráta pro malé rezidua?
- A constant penalty
- A quadratic penalty
- A binary outlier label
- No contribution to the objective
- Jak se RANSAC liší od Huberovy regrese v popsaném přístupu?
- It estimates only class probabilities
- It assigns the same squared penalty to every point
- It seeks a consensus set from repeatedly fitted subsets
- It removes the need to choose any threshold
- Velké reziduum je platná, důležitá vzácná událost. Co by měl analytik zvážit před použitím Huberovy ztráty?
- Whether rarity alone is enough to treat the event as a measurement error
- Whether Huber loss will automatically relabel the observation as an inlier
- Whether all rare observations should be removed before evaluation
- Whether downweighting that event conflicts with the decision goal
- Proč může dojít k extrémnímu reziduu, i když záznam není chybný?
- Every large residual is a data-entry mistake
- It may be a valid rare event or reflect model misspecification
- Huber loss creates all large residuals
- A linear predictor cannot have residuals
- When should a robust threshold be selected?
- Tune repeatedly on final-test errors because they best represent deployment
- Choose the threshold that minimizes training loss, then report that same training score
- Select it using training or validation data while reserving the final test set
- Use the library default without checking whether it suits the residual scale
- Which feature can remain a concern for robust regression despite reduced sensitivity to large response residuals?
- Only whether the average response residual is zero
- Only whether the residual histogram has a symmetric center
- Only whether the response variable was standardized
- Whether unusual predictor-space leverage can still affect the fit
- Why report tail performance when extreme errors matter operationally?
- A robust objective may deemphasize cases that dominate operational tail risk
- Huber loss assigns every extreme observation exactly zero influence
- Training loss alone measures accuracy on unseen extreme outcomes
- The average residual identifies the size of every tail error