Research map / Learning theory and algorithms / Prediction and decision losses
Depth is More Powerful than Width with Prediction Concatenation in Deep Forest
Shen-Huan Lyu, Yi-Xiao He, Zhi-Hua Zhou
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 |
|---|---|---|---|
| increase number of trees and training samples in the first-layer forest | Second-layer CART in deep forest · Synthetic f(x)=mean of 5 features, sigma 0.02 | effective depth of new feature: 2.4 -> 5 | Improved |
| lower first-layer prediction error (RMSE) | Second-layer CART in deep forest · Synthetic additive data | effective depth of new feature | Improved |
| use fully grown trees (tn = an) instead of trees with minimum leaf size sqrt(n) (ablation) | RF and DF · Synthetic data, n=50,000 | RMSE | Improved |
| use two-layer deep forest with M trees per layer instead of random forest with 2M trees | Tree ensemble · Synthetic data, fully grown trees, n=50,000 | RMSE vs number of trees: DF M = 20 outperforms RF M = 500 | Improved |
Closest papers by meaning
- Analyzing the tree-layer structure of Deep Forests (ICML 2021 · similarity 0.88)
- A Refined Margin Distribution Analysis for Forest Representation Learning (NeurIPS 2019 · similarity 0.83)
- The Tree Ensemble Layer: Differentiability meets Conditional Computation (ICML 2020 · similarity 0.83)
- Minimax Rates and Spectral Distillation for Tree Ensembles (NeurIPS 2026 · similarity 0.83)
- Monocular Depth Estimation Using Neural Regression Forest (CVPR 2016 · similarity 0.83)
- Mixed-curvature decision trees and random forests (ICML 2025 · similarity 0.81)
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.
