A Generalisation Signal Need Not Be a Model-Selection Signal
cs.LG, cs.AI
Submitted: 2026-09-30
Updated: 2026-09-30
Code: https://github.com/AdityaNagarsekar/A-Generalisation-Signal-Need-Not-Be-a-Model-Selection-Signal
Sources
- Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability
- Fantastic Generalization Measures are Nowhere to be Found
- Fantastic Generalization Measures and Where to Find Them
- An Evaluation of Zero-Cost Proxies -- from Neural Architecture Performance to Model Robustness
- Revisiting Generalization Measures Beyond IID: An Empirical Study under Distributional Shift
- Strong convexity-guided hyper-parameter optimization for flatter losses
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