Exact Risk Ratios for Weighted Data Selection in Linear Regression

cs.LG, math.ST, stat.TH

Submitted: 2026-08-28

Updated: 2026-10-02

Comments: 48 pages

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Exact Recovery Thresholds for Weighted Data Selection in Vector-Valued Linear Regression
• A characterization of positive spanning sets with ties to strongly connected digraphs
• Data Selection for ERMs
• Nicely structured positive bases with maximal cosine measure
• Coresets and Sketches
• Simplicial and Conical Decomposition of Positively Spanning Sets

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks