Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values

arXiv — cs.LGWednesday, January 14, 2026 at 5:00:00 AM
  • A new study introduces regression-adjusted Monte Carlo estimators for calculating Shapley values and probabilistic values, enhancing the efficiency of these computations in explainable AI. This method integrates Monte Carlo sampling with linear regression, allowing for the use of various function families, including tree-based models like XGBoost, to produce unbiased estimates.
  • This development is significant as it addresses the computational challenges associated with estimating Shapley values, which are crucial for feature attribution and data valuation in AI systems. By improving the accuracy and efficiency of these estimators, the research contributes to the advancement of explainable AI methodologies.
  • The introduction of this new approach aligns with ongoing efforts to refine Shapley values and related frameworks, such as Sparse Isotonic Shapley Regression, which seeks to overcome limitations in traditional methods. The evolution of these techniques reflects a broader trend in AI research aimed at enhancing model interpretability and robustness, particularly in decentralized learning environments and complex data scenarios.
— via World Pulse Now AI Editorial System

Was this article worth reading? Share it

Recommended apps based on your readingExplore all apps
Continue Readings
Intra-tree Column Subsampling Hinders XGBoost Learning of Ratio-like Interactions
NeutralArtificial Intelligence
A recent study has revealed that intra-tree column subsampling in XGBoost can hinder the model's ability to learn from ratio-like interactions, which are crucial for synthesizing signals from multiple raw measurements. The research utilized synthetic data with cancellation-style structures to demonstrate that subsampling reduces the model's performance in identifying significant signals.
ROSS: RObust decentralized Stochastic learning based on Shapley values
PositiveArtificial Intelligence
A new decentralized learning algorithm named ROSS has been proposed, which utilizes Shapley values to enhance the robustness of stochastic learning among agents. This approach addresses challenges posed by heterogeneous data distributions, allowing agents to collaboratively learn a global model without a central server. Each agent updates its model by aggregating cross-gradient information from neighboring agents, weighted by their contributions.

Ready to build your own newsroom?

Subscribe to unlock a personalised feed, podcasts, newsletters, and notifications tailored to the topics you actually care about