Comparison-Based Random Forests

Authors: Siavash Haghiri, Damien Garreau, Ulrike Luxburg

ICML 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In a set of comprehensive experiments, we then demonstrate that the proposed random forest is efficient both for classification and regression.
Researcher Affiliation Academia 1Department of Computer Science, University of T ubingen, Germany 2Max Planck Institute for Intelligent Systems, T ubingen, Germany.
Pseudocode Yes Algorithm 1 Comp Tree(S, n0): Supervised comparison tree construction
Open Source Code No The paper provides a link for a third-party tool (TSTE) used, but no explicit statement or link to the authors' own comparison-based random forest code is provided.
Open Datasets Yes MNIST (Le Cun et al., 1998) and Gisette are handwritten digit datasets. Isolet and UCIHAR are speech recognition and human activity recognition datasets respectively (Lichman, 2013).
Dataset Splits Yes We perform 10-fold cross-validation over n0 {1, 4, 16, 64} and M {1, 4, 16, 64, 256}. Since the regression datasets have no separate training and test set, we assign 90% of the items to the training and the remaining 10% to the test set.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper does not specify the versions of any software libraries or dependencies used in the experiments.
Experiment Setup Yes We perform 10-fold cross-validation over n0 {1, 4, 16, 64} and M {1, 4, 16, 64, 256}.