Pointwise Generalization in Deep Neural Networks
cs.LG, cond-mat.stat-mech, math.FA, math.PR, math.ST, stat.TH
Submitted: 2026-05-18
Updated: 2026-09-24
Terminology
Sources
- An Overview of Low-Rank Structures in the Training and Adaptation of Large Models
- The Two Lives of the Grassmannian
- Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data
- Neural Tangent Kernel: A Survey
- Generalization Bounds for Rank-sparse Neural Networks
- Simple and Sharp Generalization Bounds via Lifting
- A Note on Pointwise Dimensions
- Six Lectures on Linearized Neural Networks
- Uniform convergence may be unable to explain generalization in deep learning
- Neural Collapse in the Intermediate Hidden Layers of Classification Neural Networks
- Learning to Compress: Local Rank and Information Compression in Deep Neural Networks
- Opening the Black Box of Deep Neural Networks via Information
- Metric Entropy of Homogeneous Spaces
- Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination
- Deep Learning is Not So Mysterious or Different
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