Research map / Probabilistic and scientific modeling / Variational and generative sampling
Attention Implements the Fisher Geometry of Exponential Families
Bodie Rubacher
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 |
|---|---|---|---|
| replace a single shared quadratic metric with a fixed-scale H=8 multi-head curvature atlas | Poisson ICE attention model · Poisson ICE, n=1 | accuracy: 0.428 -> 0.684 | Improved |
| train a learned SPD metric on Gaussian ICE | minimal attention model · Gaussian ICE (5 seeds) | eigenvalue correlation with Bayes precision: 0.960 ± 0.005 | Improved |
| increase prompt length in Bernoulli ICE | minimal attention model · Bernoulli ICE | accuracy | Improved |
Closest papers by meaning
- Scaling Limits of Long-Context Transformers (NeurIPS 2026 · similarity 0.86)
- Bayes optimal learning of attention-indexed models (NeurIPS 2025 · similarity 0.85)
- In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention (ICML 2025 · similarity 0.85)
- High-Dimensional Learning Dynamics of Attention-Indexed Models (NeurIPS 2026 · similarity 0.85)
- Scale-invariant attention (NeurIPS 2025 · similarity 0.84)
- Recurrent Self-Attention Dynamics: An Energy-Agnostic Perspective from Jacobians (NeurIPS 2025 · similarity 0.84)
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.
