Research map / Learning theory and algorithms / Matrix and tensor methods
Scalars are universal: Equivariant machine learning, structured like classical physics
Soledad Villar, David W Hogg, Kate Storey-Fisher, Weichi Yao, Ben Blum-Smith
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| build O(5)-invariant model from scalar inputs (inner products) fed to an MLP instead of EMLP, plain MLP or MLP with augmentation | MLP · O(5)-invariant toy task | test error vs training set size | Improved |
| build O(3)-equivariant, permutation-invariant model from scalars and vectors instead of EMLP, MLP or MLP+Aug | MLP · O(3)-equivariant inertia tensor task | test error vs training set size | Improved |
| add data augmentation to a standard MLP | MLP · O(5)-invariant and O(3)-equivariant tasks | test error | Mixed |
Closest papers by meaning
- On Universality Classes of Equivariant Networks (NeurIPS 2025 · similarity 0.87)
- Permutation Equivariant Neural Networks for Symmetric Tensors (ICML 2025 · similarity 0.87)
- Learning Polynomial Problems with $SL(2, \mathbb{R})$-Equivariance (ICLR 2024 · similarity 0.86)
- Lorentz Local Canonicalization: How to make any Network Lorentz-Equivariant (NeurIPS 2025 · similarity 0.86)
- Approximately Equivariant Neural Processes (NeurIPS 2024 · similarity 0.86)
- Equivariance via Minimal Frame Averaging for More Symmetries and Efficiency (ICML 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
