Research map / Learning theory and algorithms / Prediction and decision losses
Universal consistency and minimax rates for online Mondrian Forests
Jaouad Mourtada, Stéphane Gaïffas, Erwan Scornet
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 |
|---|---|---|---|
| Replace a fixed lifetime with an increasing lifetime sequence satisfying λ_n → ∞ and λ_n^d / n → 0 | Online Mondrian Forest · Arbitrary distributions on [0,1]^d × {0,1} | consistency | Improved |
| Keep the lifetime fixed as sample size grows | Mondrian Forest · [0,1] with a fixed lifetime | classification consistency | Hurt |
| Tune the increasing lifetime as λ_n ∼ n^{1/(d+2)} | Online Mondrian Forest classifier · Lipschitz conditional probabilities, arbitrary dimension | classification error excess over Bayes error: o (n^{-1/(d+2)}) | Improved |
| Use increasing lifetime rather than constant lifetime | Mondrian Forest · Several datasets (test set) | test error | Improved |
| Use the modified increasing-lifetime method rather than Extra-Trees-1 | Online Mondrian Forest · Several datasets (test set) | test error | Improved |
| Use the modified increasing-lifetime method rather than Breiman's RF | Online Mondrian Forest · Several datasets (test set) | test error | Mixed |
Closest papers by meaning
- Minimax Rates for High-Dimensional Random Tessellation Forests (JMLR 2024 · similarity 0.88)
- Stability of Random Forests and Coverage of Random-Forest Prediction Intervals (NeurIPS 2023 · similarity 0.84)
- Minimax Rates and Spectral Distillation for Tree Ensembles (NeurIPS 2026 · similarity 0.83)
- Piecewise Constant and Linear Regression Trees: An Optimal Dynamic Programming Approach (ICML 2024 · similarity 0.82)
- A Universal Growth Rate for Learning with Smooth Surrogate Losses (NeurIPS 2024 · similarity 0.81)
- Online Consistency of the Nearest Neighbor Rule (NeurIPS 2024 · 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.
