high-dimensional datasets

4 papers

• A Unified Framework for Provably Efficient Algorithms to Estimate Shapley Values
• Distance Adaptive Beam Search for Provably Accurate Graph-Based Nearest Neighbor Search
• Proxy-SPEX: Sample-Efficient Interpretability via Sparse Feature Interactions in LLMs
• Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching