Research
Path-Sampled Integrated Gradients
arXiv:2604.14338v1 Announce Type: new Abstract: We introduce path-sampled integrated gradients (PS-IG), a framework that generalizes feature attribution by computing the expected value over baselines
arXiv:2604.14338v1 Announce Type: new Abstract: We introduce path-sampled integrated gradients (PS-IG), a framework that generalizes feature attribution by computing the expected value over baselines sampled along the linear interpolation path. We prove that PS-IG is mathematically equivalent to path-weighted integrated gradients, provided the weighting function matches the cumulative distribution function of the sampling density. This equivalence allows the stochastic expectation to be evaluated via a deterministic Riemann sum, improving the error convergence rate from O(m^{-1/2}) to O(m^{-1}) for smooth models. Furthermore, we demonstrate analytically that PS-IG functions as a variance-reducing filter against gradient noise - strictly lowering attribution variance by a factor of 1/3 under uniform sampling - while preserving key axiomatic properties such as linearity and implementation invariance.
Related
- MinShap: A Modified Shapley Value Approach for Feature Selection
- TreeGrad-Ranker: Feature Ranking via O(L)-Time Gradients for Decision Trees
- Trustworthy Feature Importance Avoids Unrestricted Permutations
- Unsupervised feature selection using Bayesian Tucker decomposition
Source: arXiv cs.LG | 2026-04-17