2 papers
cs.LG2024
SHAP values via sparse Fourier representation
Ali Gorji, Andisheh Amrollahi, Andreas Krause
SHAP (SHapley Additive exPlanations) values are a widely used method for local feature attribution in interpretable and explainable AI. We propose an efficient two-stage algorithm…
cs.LG2023
A Scalable Walsh-Hadamard Regularizer to Overcome the Low-degree Spectral Bias of Neural Networks
Ali Gorji, Andisheh Amrollahi, Andreas Krause
Despite the capacity of neural nets to learn arbitrary functions, models trained through gradient descent often exhibit a bias towards ``simpler'' functions. Various notions of sim…