Research map / Time series / Causal and generative time series
Tensor learning with orthogonal, Lorentz, and symplectic symmetries
Wilson G. Gregory, Josué Tonelli-Cueto, Nicholas F. Marshall, Andrew S. Lee, Soledad Villar
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 |
|---|---|---|---|
| use equivariant model instead of MLP baseline | stress-strain regression · TFENN dataset n=5,000 | test error: 1.586e-4 -> 4.057e-6 | Improved |
| use equivariant model instead of MLP baseline | stress-strain regression · TFENN dataset n=40,000 | test error: 2.766e-5 -> 3.310e-6 | Improved |
| add rotation data augmentation to the MLP | MLP baseline · TFENN dataset n=5,000 | test error: 1.586e-4 -> 2.020e-5 | Improved |
| use equivariant model instead of TFENN | stress-strain regression · TFENN dataset n=20,000 | test error: 3.0e-5 -> 7.748e-7 | Improved |
| use equivariant model instead of MLP augmented | path signature · O(d) paths | signature test error: 0.007 -> 0.002 | Improved |
| use equivariant model instead of MLP augmented | path signature · Lorentz paths | signature test error: 0.186 -> 0.005 | Improved |
| use learned model instead of discrete signature | path signature · Lorentz paths | signature test error: 1.489 -> 0.005 | Improved |
| use equivariant model instead of SoS with Random covariance | sparse vector, Accept/Reject · Accept/Reject Random | squared correlation: 0.610 -> 0.938 | Improved |
| use equivariant model instead of SoS with Identity covariance | sparse vector, Accept/Reject · Accept/Reject Identity | squared correlation: 0.606 -> 0.190 | Hurt |
| use equivariant model instead of SoS | sparse vector, Bernoulli-Gaussian · Bernoulli-Gaussian Random | squared correlation: 0.962 -> 0.937 | Hurt |
| use equivariant model instead of SoS | sparse vector, Bernoulli-Rademacher · Bernoulli-Rademacher Random | squared correlation: 0.526 -> 0.957 | Improved |
| use equivariant model instead of MLP baseline | sparse vector, Bernoulli-Rademacher · Bernoulli-Rademacher Random | squared correlation: 0.923 -> 0.957 | Improved |
Closest papers by meaning
- Permutation Equivariant Neural Networks for Symmetric Tensors (ICML 2025 · similarity 0.90)
- Learning symmetries via weight-sharing with doubly stochastic tensors (NeurIPS 2024 · similarity 0.87)
- The Price of Freedom: Exploring Expressivity and Runtime Tradeoffs in Equivariant Tensor Products (ICML 2025 · similarity 0.87)
- A Space Group Symmetry Informed Network for O(3) Equivariant Crystal Tensor Prediction (ICML 2024 · similarity 0.87)
- Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Products (ICLR 2024 · similarity 0.86)
- Improving Equivariant Networks with Probabilistic Symmetry Breaking (ICLR 2025 · 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.
