Research map / Architectures and efficiency / RNNs and normalization
Lower Bounds on the Depth of Integral ReLU Neural Networks via Lattice Polytopes
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 |
|---|---|---|---|
| Restrict network weights to integers | ReLU networks computing max{0, x₁, …, xₙ} · max{0, x₁, …, xₙ} | necessary hidden layers: two hidden layers -> $\lceil\log_2(n)\rceil$ hidden layers | Helped |
| Add a hidden layer | Integral ReLU networks · Functions representable on ℝⁿ | representable function class | Helped |
| Allow arbitrary, potentially non-integer weights | ReLU networks · max{0, x₁, …, xₙ} | proven necessary hidden layers: logarithmic -> two hidden layers | Hurt |
Closest papers by meaning
- Depth-Bounds for Neural Networks via the Braid Arrangement (NeurIPS 2025 · similarity 0.90)
- On the Expressiveness of Rational ReLU Neural Networks With Bounded Depth (ICLR 2025 · similarity 0.88)
- Topological obstruction to the training of shallow ReLU neural networks (NeurIPS 2024 · similarity 0.86)
- Most ReLU Networks Admit Identifiable Parameters (NeurIPS 2026 · similarity 0.85)
- Defining Neural Network Architecture through Polytope Structures of Datasets (ICML 2024 · similarity 0.85)
- Compelling ReLU Networks to Exhibit Exponentially Many Linear Regions at Initialization and During Training (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.