Discovering Symmetries in Neural Network Parameter Spaces
cs.LG
Submitted: 2026-09-27
Updated: 2026-09-27
Terminology
Sources
- Symmetry-invariant optimization in deep networks
- Universal approximation and model compression for radial neural networks
- Explicit Discovery of Nonlinear Symmetries from Dynamic Data
- Frame Averaging for Invariant and Equivariant Network Design
- Symmetry Discovery Beyond Affine Transformations
- Continuous Symmetry Discovery and Enforcement Using Infinitesimal Generators of Multi-parameter Group Actions
- GLU Variants Improve Transformer
- Integrating infinitesimal (super) actions
- Self-Supervised Detection of Perfect and Partial Input-Dependent Symmetries
- Complete Identification of Deep ReLU Networks through ukasiewicz Logic
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