Research map / Learning theory and algorithms / Prediction and decision losses
Constrained Monotonic Neural Networks
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 proposed constrained monotonic network instead of Cert-Mono | Partially monotonic models · COMPAS | test accuracy: 68.8% ± 0.2% -> 68.9% ± 0.5% | Helped |
| Use the proposed constrained monotonic network instead of Cert-Mono | Partially monotonic models · Blog Feedback | RMSE: 0.158 ± 0.001 -> 0.156 ± 0.001 | Helped |
| Use the proposed constrained monotonic network instead of Cert-Mono | Partially monotonic models · Loan Defaulter | test accuracy: 65.2% ± 0.1% -> 65.3% ± 0.0003% | Helped |
Closest papers by meaning
- Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations (ICML 2025 · similarity 0.92)
- Certified Monotonic Neural Networks (NeurIPS 2020 · similarity 0.89)
- Unconstrained Monotonic Neural Networks (NeurIPS 2019 · similarity 0.89)
- Counterexample-Guided Learning of Monotonic Neural Networks (NeurIPS 2020 · similarity 0.88)
- Smooth Min-Max Monotonic Networks (ICML 2024 · similarity 0.88)
- Robustly Learning Monotone Single-Index Models (NeurIPS 2025 · similarity 0.83)
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.