Research map / Optimization / Optimizers
Splitting Steepest Descent for Growing Neural Architectures
Lemeng Wu, Dilin Wang, Qiang Liu
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 progressive neuron splitting to grow a compact DS-CNN | Compact DS-CNN · Google Speech Commands | accuracy: 94.85 -> 95.36 | Improved |
| Use progressive neuron splitting instead of the DS-CNN baseline | Compact DS-CNN · Google Speech Commands | Params (K): 413.7 -> 282.6 | Improved |
| Use progressive neuron splitting instead of the DS-CNN baseline | Compact DS-CNN · Google Speech Commands | Ops (M): 56.9 -> 39.2 | Improved |
| Choose neurons with the most negative splitting indexes and split along their minimum-eigenvalue directions | Progressive neuron-splitting method · Toy RBF neural network | loss | Improved |
Closest papers by meaning
- Gradient Descent Provably Optimizes Over-parameterized Neural Networks (ICLR 2019 · similarity 0.88)
- Flavors of Margin: Implicit Bias of Steepest Descent in Homogeneous Neural Networks (ICLR 2025 · similarity 0.87)
- SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures (NeurIPS 2025 · similarity 0.86)
- GradMetaNet: An Equivariant Architecture for Learning on Gradients (NeurIPS 2025 · similarity 0.86)
- Learning Provably Improves the Convergence of Gradient Descent (NeurIPS 2025 · similarity 0.86)
- The Benefits of Reusing Batches for Gradient Descent in Two-Layer Networks: Breaking the Curse of Information and Leap Exponents (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.
