Research map / Learning theory and algorithms / Prediction and decision losses
Online Learning With Bayesian Classification Trees
Check 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 Bayesian online trees instead of the strongest reported online forest baseline | BOF · G50c | classification error (%): 13.8 ±1.79 -> 7.74 ±1.29 | Helped |
| Use Bayesian online trees instead of the strongest reported online forest baseline | BOF · dna (180 features) | classification error (%): 7.36 ±0.32 -> 5.78 ±0.31 | Helped |
| Use Bayesian online trees instead of the strongest reported online forest baseline | BOF · dna (60 features) | classification error (%): 5.77 ±0.56 -> 4.87 ±0.19 | Helped |
| Use Bayesian online trees instead of the strongest reported online forest baseline | BOF · satimages | classification error (%): 10.4 ±0.13 -> 11.14 ±0.30 | Hurt |
| Use Bayesian online trees instead of the strongest reported online forest baseline | BOF · USPS | classification error (%): 6.79 ±0.23 -> 6.17 ±0.28 | Helped |
| Add random feature projections (ablation) | BOF · G50c | classification error (%): 7.74 ±1.29 -> 3.64 ±0.25 | Helped |
| Add random feature projections (ablation) | BOF · satimages | classification error (%): 11.14 ±0.30 -> 13.25 ±0.20 | Hurt |
| Add bagging (ablation) | BOF · classification ML datasets | classification error (%): Table 1 reports BOF and BOF-B values across G50c, dna, satimages and USPS | No clear effect |
| Use random feature projections and bagging together (ablation) | BOF · classification ML datasets | classification error (%): Table 1 reports BOF-PB values across G50c, dna, satimages and USPS | Mixed |
| Increase the ensemble from 1 to 8 BOF trees (ablation) | BOF · G50c | classification error (%): 8.1 -> 7.7 | Helped |
| Increase the ensemble from 1 to 8 BOF trees (ablation) | BOF · USPS | classification error (%): 8.3 -> 6.2 | Helped |
| Use diagonal rather than full covariance matrices (ablation) | BOF-S on Kinect body-part recognition · Kinect | pixel labeling accuracy | No clear effect |
Closest papers by meaning
- Optimal Classification Trees for Continuous Feature Data Using Dynamic Programming with Branch-and-Bound (AAAI 2025 · similarity 0.84)
- Learning Small Decision Trees with Few Outliers: A Parameterized Perspective (AAAI 2024 · similarity 0.84)
- Symbolic Regression Enhanced Decision Trees for Classification Tasks (AAAI 2024 · similarity 0.83)
- Learning Decision Trees and Forests with Algorithmic Recourse (ICML 2024 · similarity 0.83)
- Online Classification with Predictions (NeurIPS 2024 · similarity 0.83)
- Improving Decision Trees through the Lens of Parameterized Local Search (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.