Research map / Probabilistic and scientific modeling / Differential equations and PDEs
Principles of Riemannian Geometry in Neural Networks
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| increase depth from 10 to 20 or 40 layers in C1 residual network (smaller Delta l) (ablation) | C1 residual network on 2D spirals · Spiral toy dataset (2D) | error rate: 1% -> 0.0% | Helped |
| use larger batch size (1000 vs 300) during training (ablation) | C1 network on 2D spirals · Spiral toy dataset (2D), batch size | qualitative topology preservation | Helped |
| residual (C1) connections and momentum (C2) versus standard feedforward C0 network | 2D spiral untangling networks · Spiral toy dataset (2D) | error rate | No clear effect |
| share parameters between residual blocks at same dimension (ImageNet, from cited work [4]) | deep residual convolution network · ImageNet | accuracy: cost of 0.2% | Hurt |
Closest papers by meaning
- Building Transformation Layers for Riemannian Neural Networks (NeurIPS 2026 · similarity 0.88)
- Matrix Manifold Neural Networks++ (ICLR 2024 · similarity 0.88)
- A Lie Group Approach to Riemannian Batch Normalization (ICLR 2024 · similarity 0.86)
- RMLR: Extending Multinomial Logistic Regression into General Geometries (NeurIPS 2024 · similarity 0.86)
- A Riemannian Framework for Learning Reduced-order Lagrangian Dynamics (ICLR 2025 · similarity 0.86)
- Data-free Neural Representation Compression with Riemannian Neural Dynamics (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.