Research map / Architectures and efficiency / RNNs and normalization
On the Expressive Power of Permutation-Equivariant Weight-Space Networks
Adir Dayan, Yam Eitan, Haggai Maron
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 |
|---|---|---|---|
| add Output Capacity Expansion (k=8 output MLP ensemble) | GMN · MNIST INR dilation | MSE (x1e-2): 1.96 -> 1.06 | Improved |
| add Output Capacity Expansion (k=8 output MLP ensemble) | DWS · MNIST INR dilation | MSE (x1e-2): 2.29 -> 1.36 | Improved |
| increase output ensemble size k (ablation) | DWS · MNIST INR dilation | MSE: up to 41% | Improved |
| increase output ensemble size k (ablation) | GMN · MNIST INR dilation | MSE: up to 46% | Improved |
Closest papers by meaning
- Universal Neural Functionals (NeurIPS 2024 · similarity 0.91)
- On Universality Classes of Equivariant Networks (NeurIPS 2025 · similarity 0.88)
- A Tale of Two Symmetries: Exploring the Loss Landscape of Equivariant Models (NeurIPS 2025 · similarity 0.87)
- A Characterization Theorem for Equivariant Networks with Point-wise Activations (ICLR 2024 · similarity 0.87)
- The impact of allocation strategies in subset learning on the expressive power of neural networks (ICLR 2025 · similarity 0.86)
- Towards Scalable and Versatile Weight Space Learning (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.
