Research map / Architectures and efficiency / RNNs and normalization
Exploiting weight-space symmetries for approximating curvature
Artem Artemev, Rui Xia, Benjamin M. Boyd, Youjing Yu, Felix Dangel, Guillaume Hennequin, Alberto Bernacchia
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 block-diagonal restriction of H*_g (ablation) | Symo Hessian approximation · Teacher-student MLP (D=19,850), random-direction secant cosine similarity | cosine similarity | No clear effect |
| use identity weight covariance (H*_g) instead of inverting it (H*_PD) (ablation) | Symo Hessian approximation · Gradient-direction secant test | cosine similarity | Improved |
| use Hessian at orbit-averaged parameters H* alone (ablation) | Symo Hessian approximation · Teacher-student MLP (D=19,850), random-direction secant cosine similarity | cosine similarity: between 0.1 and 0.2 -> near zero | Hurt |
| use Symo instead of Adam | MNIST autoencoder and nanoGPT · MNIST autoencoder / nanoGPT | training curves | Improved |
| use largest symmetry group (all layers permuted) in Symo (ablation) | Symo · Deep MLP autoencoder | training curves | Improved |
| use smaller group with odd-layer permutation and block-diagonal Hessian (ablation) | Symo · Deep MLP autoencoder | training curves | No clear effect |
Closest papers by meaning
- Global curvature for second-order optimization of neural networks (ICML 2025 · similarity 0.89)
- RMLR: Extending Multinomial Logistic Regression into General Geometries (NeurIPS 2024 · similarity 0.86)
- Symmetry Induces Structure and Constraint of Learning (ICML 2024 · similarity 0.85)
- A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models (NeurIPS 2025 · similarity 0.85)
- Learning symmetries via weight-sharing with doubly stochastic tensors (NeurIPS 2024 · similarity 0.85)
- Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks (NeurIPS 2024 · similarity 0.85)
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.
