Cone Extended Rayleigh Quotients for Directed Graph Learning: Minimax Spectral Certificates, Sensitivity, and Adaptive Control

arXiv:2608.27122 · cs.LG · Submitted 2026-08-27 · Read on arXiv

cs.LG

Submitted: 2026-08-27

Updated: 2026-08-27

Terminology

• Accuracy — 13× in this paper · explained in 1 episode
• Robustness — 2× in this paper · explained in 5 episodes
• Adaptive Strategy — 1× in this paper · explained in 1 episode
• Adjacency Matrix — 1× in this paper · explained in 1 episode
• Admissibility — 1× in this paper · explained in 2 episodes
• Approximation Bound — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Homogeneity — 1× in this paper · explained in 2 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Spectral clustering — 1× in this paper · explained in 2 episodes
• Twelfth International Conference on Learning Representations — 1× in this paper

Sources

• On the Minimax Bifurcation Formula
• Cone Minimax Principles for Non-Selfadjoint Operator Pencils
• Spectral-based Graph Convolutional Network for Directed Graphs
• Directed Graph Convolutional Network

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: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks