DNNs, Dataset Statistics, and Correlation Functions
physics.hist-ph, cond-mat.stat-mech, cs.LG
Submitted: 2025-11-18
Updated: 2026-10-30
Terminology
Sources
- The Representational Status of Deep Learning Models
- Modelling the influence of data structure on learning in neural networks: the hidden manifold model
- Generalization in Deep Learning
- The Underlying Scaling Laws and Universal Statistical Structure of Complex Datasets
- Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning
- Neural networks trained with SGD learn distributions of increasing complexity
- Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild
- The information bottleneck method
- Understanding deep learning requires rethinking generalization
Related papers
- A Personal History in Quantum Foundations: an Oral History Interview
- On Algebraic Background-Independence
- Determinism and Indeterminism as Model Artefacts: Toward a Model-Invariant Ontology of Physics
- Schr"odinger's unpublished hidden-variable model in the 1944-45 debate over the "Collapse of Determinism"
- From the Light Quantum to the Photon: The Evolution of a Physical Concept
- Between Heisenberg and Feynman: Ettore Majorana's Reflections on the Meaning of Quantum Theory