AI Paper Atlas

Research map / Learning theory and algorithms / Matrix and tensor methods

Sparse Projection Oblique Randomer Forests

Tyler M. Tomita, James Browne, Cencheng Shen, Jaewon Chung, Jesse L. Patsolic, Benjamin Falk, Carey E. Priebe, Jason Yim, Randal Burns, Mauro Maggioni, Joshua T. Vogelstein

JMLR 2020 · Learning theory and algorithms › Matrix and tensor methods · approach: Sparse regression with guarantees

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 changedWhereMeasuredEffect
replace axis-aligned splits with sparse random oblique projectionsRandom Forest · Consistency problem (p = 2)error rate: lower bound of error 1/6 for Random ForestImproved
replace axis-aligned splits with sparse random oblique projectionsRandom Forest · UCI hill_valley (5-fold CV)Cohen's kappa (%): 12 -> 100Improved
replace axis-aligned splits with sparse random oblique projectionsRandom Forest · UCI hill_valley-noise (5-fold CV)Cohen's kappa (%): 3 -> 90Improved
replace axis-aligned splits with sparse random oblique projectionsRandom Forest · UCI balance_scale (5-fold CV)Cohen's kappa (%): 77 -> 94Improved
replace axis-aligned splits with sparse random oblique projectionsRandom Forest · UCI adult (5-fold CV)Cohen's kappa (%): 82.42 -> 82.38No clear effect
use sparse random projections instead of Random Forest axis-aligned splitsRandom Forest · Sparse parity (p = 20)error rateImproved
use SPORF instead of Forest-RC on the orthant problemForest-RC · Orthant (p = 6)error rateImproved
add many noise dimensions (10, 100, 1000) to UCI datasets, SPORF versus CCF and RerFSPORF · UCI with Gaussian noise dimensionsmean Cohen's kappaImproved
use default d = p, lambda = 3/p instead of tuned best d = p^2, lambda = 4/pSPORF · UCI default hyperparametersmedian rank of kappa: best d = p^2, lambda = 4/p; default d = p, lambda = 3/pMixed
sample d greater than p projections per node (ablation)SPORF · Sparse parity (p = 20, n = 5000)error rate and training timeMixed
pack the trained forest (Forest Packing) for predictionSPORF · MNIST, Higgs, p53 prediction timeprediction time: roughly ten times faster than XGBoost, over 100 times faster than standard SPORFImproved
sample sparse lambda-density random matrices versus fixed-sparsity projections in Forest-RC (ablation)SPORF · Sparse parity (n = 5000) and orthant (n = 400)error rate vs lambdaImproved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy