So, I was wondering how LIME's linear model approach compares with other explanation metrics, in special, with Mutual Information? For those unfamiliar with how LIME works:
- Choose the instance you want to explain
- Probe your model with a few perturbations on that instance
- Fit a linear model to those points, points closer to the original instance are worth more (weighted heavier)
- You can now look to the (simpler) linear model, instead of your RBF-kernel SVM (much harder to interpret)
What would be advantages and disadvantages of using a different "model" in step 3, in this, calculating the mutual information of the model-assigned label and each of the features?