Research map / Learning theory and algorithms / Combinatorial and search optimization
Cheap Orthogonal Constraints in Neural Networks: A Simple Parametrization of the Orthogonal and Unitary Group
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 |
|---|---|---|---|
| Use the exponential parametrization instead of the strongest reported baseline | Exprnn versus URNN · MNIST | accuracy: 0.984 -> 0.987 | Helped |
| Use the exponential parametrization instead of the strongest reported baseline | Exprnn versus SCORNN · p-MNIST | accuracy: 0.965 -> 0.966 | Helped |
| Use the exponential parametrization instead of the strongest reported baseline | Exprnn versus SCORNN · TIMIT test | MSE: 7.36 -> 4.38 | Helped |
| Use the exponential parametrization rather than the compared architectures | Exprnn · Copying memory (L=2000) | convergence | Helped |
Closest papers by meaning
- Efficient Orthogonal Parametrisation of Recurrent Neural Networks Using Householder Reflections (ICML 2017 · similarity 0.89)
- Lie Group Decompositions for Equivariant Neural Networks (ICLR 2024 · similarity 0.86)
- Improving Equivariant Model Training via Constraint Relaxation (NeurIPS 2024 · similarity 0.86)
- Global Minimizers of $\ell^p$-Regularized Objectives Yield the Sparsest ReLU Neural Networks (NeurIPS 2025 · similarity 0.86)
- Neural Characteristic Activation Analysis and Geometric Parameterization for ReLU Networks (NeurIPS 2024 · similarity 0.86)
- Simple Orthogonal Graph Representation Learning (Student Abstract) (AAAI 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.