Hidden Gauge Controls Feature Specialization in ReLU Networks
cs.LG, cs.AI
Submitted: 2026-08-07
Updated: 2026-09-13
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Path-conditioned training: a principled way to rescale ReLU neural networks
- Abide by the Law and Follow the Flow: Conservation Laws for Gradient Flows
- Intrinsic training dynamics of deep neural networks
- Scale redundancy and soft gauge fixing in positively homogeneous neural networks
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