Research map / Learning theory and algorithms / Prediction and decision losses
ThunderGBM: Fast GBDTs and Random Forests on GPUs
Zeyi Wen, Hanfeng Liu, Jiashuai Shi, Qinbin Li, Bingsheng He, Jian Chen
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 |
|---|---|---|---|
| use ThunderGBM instead of XGBoost on GPU | GBDT training · higgs (reg) | training time (s): 9.9 -> 6.6 | Improved |
| use ThunderGBM instead of XGBoost on CPUs | GBDT training · news20 (clf) | training time (s): 287 -> 5.8 | Improved |
| use ThunderGBM instead of LightGBM on GPU | GBDT training · log1p (reg) | training time (s): 261 -> 25.6 | Improved |
| use ThunderGBM instead of LightGBM on GPU | GBDT training · yahoo (rnk) | training time (s): 29.4 -> 2.4 | Improved |
| use ThunderGBM instead of XGBoost on GPU | GBDT training · yahoo (rnk) | training time (s): 2.4 -> 2.4 | No clear effect |
| use ThunderGBM instead of XGBoost on GPU | GBDT training · log1p (reg), 4M dimensions | training success: oom -> 25.6 | Improved |
| use ThunderGBM instead of CatBoost on CPUs | GBDT training · higgs (reg) | training time (s): 67.9 -> 6.6 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- LightGBM — LightGBM: A Highly Efficient Gradient Boosting Decision Tree (NeurIPS 2017) · better on 8 of 8 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- SketchBoost: Fast Gradient Boosted Decision Tree for Multioutput Problems (NeurIPS 2022 · similarity 0.88)
- LightGBM: A Highly Efficient Gradient Boosting Decision Tree (NeurIPS 2017 · similarity 0.87)
- Quantized Training of Gradient Boosting Decision Trees (NeurIPS 2022 · similarity 0.87)
- NRGBoost: Energy-Based Generative Boosted Trees (ICLR 2025 · similarity 0.82)
- Very Fast Bayesian Additive Regression Trees on GPU (NeurIPS 2026 · similarity 0.80)
- Gradient Regularized Newton Boosting Trees with Global Convergence (NeurIPS 2026 · similarity 0.80)
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.
