Research map / Optimization / Implicit bias and generalization
Is Deeper Better only when Shallow is Good?
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 |
|---|---|---|---|
| increase network depth on 2D Cantor distribution with coarse approximation curve | ReLU networks trained with Adam · 2D Cantor set depth 5 | test error | Helped |
| make the distribution finer (weight on fine details) instead of coarse | depth 5 network · 2D Cantor set depth 5 | test error | Hurt |
| vary approximation curve (coarse vs fine) for Sierpinsky Triangle | wide depth 5 network · Sierpinsky Triangle | test error | No clear effect |
Closest papers by meaning
- On the Depth of Deep Neural Networks: A Theoretical View (AAAI 2016 · similarity 0.89)
- The Expressive Power of Neural Networks: A View from the Width (NeurIPS 2017 · similarity 0.88)
- On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization (ICML 2018 · similarity 0.88)
- The Implicit Bias of Depth: From Neural Collapse to Softmax Codes (ICML 2026 · similarity 0.88)
- Position: A Theory of Deep Learning Must Include Compositional Sparsity (ICML 2025 · similarity 0.87)
- Tensor Programs VI: Feature Learning in Infinite Depth Neural Networks (ICLR 2024 · similarity 0.87)
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.