Entity · paper

Conservation Laws from Data Symmetry in Neural Networks

paperactiveconservation-laws-from-data-symmetry-in-neural-networks-cd3f547c·1 events·first seen Jun 10, 2026

Aliases: Conservation Laws from Data Symmetry in Neural Networks

Co-occurring entities

More like this (12)

How Width and Data Shape Generalization Scaling Laws in Quadratic Neural Networks Scaling Laws for Neural Language Models Preserving Plasticity in Continual Learning via Dynamical Isometry 1-Lipschitz Neural Networks on Hadamard Manifolds Physics-Informed Neural Networks Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal Topological Neural Operators Neural Collapse Is Forbidden: Information Floors in Language Models Prior-Data Fitted Networks Recoverable but Not Stationary: Local Linear Structures in Weights and Activations Binarized Neural Network The Stable Recovery Manifold: Geometric Principles Governing Recoverability in Continual Learning

Recent events (1)

4arXiv · cs.LG·Jun 10, 2026·source ↗

Conservation laws from data symmetry in neural network gradient-flow training

A new arXiv preprint investigates whether intrinsic symmetries in training data produce conserved quantities during gradient-flow training of neural networks. The authors prove that for analytic, non-polynomial loss functions, data symmetries generically do not induce additional integrals of motion, but for MSE loss, data augmentation can yield extra conserved quantities. They introduce a framework of 'tensorizable networks'—architectures including linear, polynomial, and Lightning Attention networks—where parameter and input dependence can be separated via an intermediate representation.

Training Infrastructure Lightning Attention Conservation Laws from Data Symmetry in Neural Networks