Enforcing Symmetries on Pre-trained ML Models for Physics
cs.LG, physics.comp-ph, stat.ML
Submitted: 2026-11-06
Updated: 2026-11-06
Code: https://github.com/wenjie271/Post-hoc-group-averaging
Terminology
Sources
- On the Benefits of Invariance in Neural Networks
- Steerable CNNs
- N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials
- e3nn: Euclidean Neural Networks
- A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups
- Incorporating Symmetry into Deep Dynamics Models for Improved Generalization
- A Galois theorem for machine learning: Functions on symmetric matrices and point clouds via lightweight invariant features
- Tensor learning with orthogonal, Lorentz, and symplectic symmetries
- On the Sample Complexity of Learning under Invariance and Geometric Stability
- Achieving Approximate Symmetry Is Exponentially Easier than Exact Symmetry
- Group Averaging for Physics Applications: Accuracy Improvements at Zero Training Cost
- Frame Averaging for Invariant and Equivariant Network Design
- Equivariance via Minimal Frame Averaging for More Symmetries and Efficiency
- Lie Algebra Canonicalization: Equivariant Neural Operators under arbitrary Lie Groups
- Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance
- Learned Coarse Models for Efficient Turbulence Simulation
- Multiple Physics Pretraining for Physical Surrogate Models
- UPS: Efficiently Building Foundation Models for PDE Solving via Cross-Modal Adaptation
- OmniArch: Building Foundation Model For Scientific Computing
- The Multimodal Universe: Enabling Large-Scale Machine Learning with 100TB of Astronomical Scientific Data
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis