Research map / Learning theory and algorithms / Prediction and decision losses
Deep Lattice Networks and Partial Monotonic Functions
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 a deep lattice architecture instead of Crystals | User Intent classification · User Intent | test accuracy: 72.01% -> 72.48% | Helped |
| Use a deep lattice architecture instead of Crystals | Adult classification · Adult | test accuracy: 85.87% -> 86.08% | Helped |
| Use a deep lattice architecture instead of Crystals | Rater Score prediction · Rater Score | test MSE: 1.2109 -> 1.2096 | Helped |
| Use a deep lattice architecture instead of Crystals | Usefulness classification · Usefulness | test accuracy: 65.13% -> 65.26% | Helped |
| Use a final lattice rather than a final linear layer | Cal-Lin-Cal-EnsLat-Cal-Lin · User Intent | test accuracy: 72.48% -> 72.59% | Mixed |
Closest papers by meaning
- Certified Monotonic Neural Networks (NeurIPS 2020 · similarity 0.90)
- Hierarchical Lattice Layer for Partially Monotone Neural Networks (NeurIPS 2022 · similarity 0.87)
- Scalable Monotonic Neural Networks (ICLR 2024 · similarity 0.87)
- Smooth Min-Max Monotonic Networks (ICML 2024 · similarity 0.86)
- Advancing Constrained Monotonic Neural Networks: Achieving Universal Approximation Beyond Bounded Activations (ICML 2025 · similarity 0.85)
- Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks (ICLR 2024 · similarity 0.84)
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.