Theory-Guided Instance-Dependent Early Stopping via Second-Order Loss Dynamics

cs.LG, cs.CV

Submitted: 2026-10-17

Updated: 2026-10-17

Comments: 29 pages, 11 figures, 12 tables. Code available at https://github.com/ShoebAhad/theory-guided-ies

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

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