Research map / Learning theory and algorithms / Prediction and decision losses
Quantifying Uncertainty in Online Regression Forests
Theodore Vasiloudis, Gianmarco De Francisci Morales, Henrik Boström
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 conformal prediction (CPExact) instead of Gaussian quantiles | online regression forest · Small-scale data | mean error rate: 0.4 -> 0.1 desired; CPExact 0.08 at alpha 0.1 | Improved |
| use OnlineQRF instead of Mondrian Forest | online regression forest · Small-scale data, significance 0.1 | mean error rate: 0.13 -> 0.07 | Improved |
| use OnlineQRF instead of Mondrian Forest | online regression forest · Small-scale data, significance 0.01 | mean error rate: 0.062 -> 0.015 | Improved |
| use CPApproximate instead of CPExact | online conformal prediction · Small-scale data, significance 0.1 | relative interval size: 0.57 -> 0.48 | Improved |
| use OnlineQRF instead of CPExact | online regression forest · Small-scale data, significance 0.01 | relative interval size: 0.944 -> 0.510 | Improved |
| use OnlineQRF instead of Mondrian Forest | online regression forest · Small-scale data, significance 0.01 | relative interval size: 0.460 -> 0.510 | Hurt |
| use OnlineQRF instead of Mondrian Forest | online regression forest · Small-scale data | average running time (seconds): 41.6 -> 5.4 | Improved |
| use OnlineQRF instead of Mondrian Forest | online regression forest · Flight delays | average running time (seconds): 6340 -> 836 | Improved |
| use CPApproximate instead of CPExact | online conformal prediction · Flight delays | average running time (seconds): 27863 -> 899 | Improved |
| use CPApproximate instead of CPExact | online conformal prediction · Small-scale data | average running time (seconds): 102.3 -> 5.7 | Improved |
| use OnlineQRF instead of Mondrian Forest | online regression forest · Friedman (concept drift) | average running time (seconds): 2380 -> 114 | Improved |
| lower the significance level from 0.1 to 0.01 | Mondrian Forest · Small-scale data | mean error rate: 0.13 -> 0.062 against target 0.01 | Hurt |
Closest papers by meaning
- Online Algorithms with Uncertainty-Quantified Predictions (ICML 2024 · similarity 0.89)
- Beyond the Norms: Detecting Prediction Errors in Regression Models (ICML 2024 · similarity 0.87)
- Error-quantified Conformal Inference for Time Series (ICLR 2025 · similarity 0.86)
- Algorithms with Calibrated Machine Learning Predictions (ICML 2025 · similarity 0.86)
- Learning from Uncertain Data: From Possible Worlds to Possible Models (NeurIPS 2024 · similarity 0.85)
- Online Conformal Prediction via Online Optimization (ICML 2025 · similarity 0.85)
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.
