120Compare SHAP and LIME for explaining model predictions. What does SHAP guarantee that LIME does not?▼mediumGoogleMicrosoftAmazon2 replies◆ premiumBoth explain a single prediction by attributing it to features, but only one rests on a uniqueness theorem. The signal is knowing SHAP's game-theory guarantees, LIME's instability, and when each is the right tool. Here is the answer.Open full answer →
121Explain integrated gradients for attribution. Why use it over raw gradients, and how do you pick the baseline?▼hardGoogleGoogle DeepMindNVIDIA1 replies◆ premiumRaw gradient saliency maps are noisy and saturate. Integrated gradients fixes both with two axioms and a path integral, but the baseline choice quietly decides the answer. Here is what a careful candidate explains.Open full answer →
