Research map / Learning theory and algorithms / Prediction and decision losses
Learning Binary Decision Trees by Argmin Differentiation
Valentina Zantedeschi, Matt Kusner, Vlad Niculae
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 |
|---|---|---|---|
| Learn discrete tree traversal and pruning parameters alongside continuous split and prediction parameters using argmin differentiation | Binary decision trees · YEAR | MSE/ER: 97.4 \pm 0.4 -> 77.9\pm0.4 | Improved |
| Learn discrete tree traversal and pruning parameters alongside continuous split and prediction parameters using argmin differentiation | Binary decision trees · MICROSOFT | MSE/ER: 0.691 \pm 3\text{e-}3 -> 0.573\pm2\text{e-}3 | Improved |
| Learn discrete tree traversal and pruning parameters alongside continuous split and prediction parameters using argmin differentiation | Binary decision trees · YAHOO | MSE/ER: 0.619 \pm 3\text{e-}3 -> 0.591 \pm 1\text{e-}3 | Improved |
| Learn discrete tree traversal and pruning parameters alongside continuous split and prediction parameters using argmin differentiation | Binary decision trees · CLICK | MSE/ER: 0.3780 \pm 6\text{e-}3 -> 0.3340 \pm 3\text{e-}4 | Improved |
| Learn discrete tree traversal and pruning parameters alongside continuous split and prediction parameters using argmin differentiation | Binary decision trees · HIGGS | MSE/ER: 0.3220 \pm 1\text{e-}3 -> 0.2201\pm3\text{e-}4 | Improved |
| Use unbounded rather than bounded maximal depth for CART | CART · YEAR, MICROSOFT, YAHOO, CLICK, HIGGS | MSE/ER: 97.4 ± 0.4 -> 96.0 ± 0.4; 0.691 ± 3e-3 -> 0.599 ± 1e-3; 0.619 ± 3e-3 -> 0.678 ± 17e-3; 0.3780 ± 6e-3 -> 0.3426 ± 11e-3; | Mixed |
Closest papers by meaning
- Near-Optimal Decision Trees in a SPLIT Second (ICML 2025 · similarity 0.86)
- Improving Decision Trees through the Lens of Parameterized Local Search (NeurIPS 2025 · similarity 0.86)
- Optimal Decision Tree Pruning Revisited: Algorithms and Complexity (ICML 2025 · similarity 0.86)
- Learning Small Decision Trees with Few Outliers: A Parameterized Perspective (AAAI 2024 · similarity 0.86)
- Branches: Efficiently Seeking Optimal Sparse Decision Trees via AO* (ICML 2025 · similarity 0.86)
- TREE-G: Decision Trees Contesting Graph Neural Networks (AAAI 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.
