Research map / Architectures and efficiency / RNNs and normalization
Low Tensor Rank Learning of Neural Dynamics
Arthur Pellegrino, N Alex Cayco Gajic, Angus Chadwick
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 ltrRNN with 5 components instead of the full tensor RNN (ablation) | ltrRNN · macaque motor learning data | held-out unexplained variance | No clear effect |
| allow weights to vary over trials (full tensor RNN) versus static RNN (ablation) | RNN · macaque motor learning data | variance explained: ~5% difference | Improved |
| ltrRNN instead of truncated SVD and PARAFAC at low ranks | low-rank models · macaque motor learning data | held-out unexplained variance | Improved |
| double neurons from 200 to 400 (370 trials) | ltrRNN · training time | training time: 12min -> 22min | Hurt |
| double trials from 370 to 740 (200 neurons) | ltrRNN · training time | training time: 12min -> 16min | Hurt |
Closest papers by meaning
- Learning Reveals Invisible Structure in Low-Rank RNNs (NeurIPS 2026 · similarity 0.89)
- How connectivity structure shapes rich and lazy learning in neural circuits (ICLR 2024 · similarity 0.87)
- Inferring stochastic low-rank recurrent neural networks from neural data (NeurIPS 2024 · similarity 0.87)
- Analyzing Neural Scaling Laws in Two-Layer Networks with Power-Law Data Spectra (ICLR 2025 · similarity 0.85)
- Low Rank Gradients and Where to Find Them (NeurIPS 2025 · similarity 0.85)
- Low-Rank Tensor Transitions (LoRT) for Transferable Tensor Regression (ICML 2025 · 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.
