AI Paper Atlas

Research map / Learning theory and algorithms / Prediction and decision losses

Approximation-Free Differentiable Oblique Decision Trees

Subrat Prasad Panda, Blaise Genest, Arvind Easwaran

JMLR 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Optimal decision tree learning · 0 citations (OpenAlex)

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 STE with annealed Top-k selection (ablation)DTSemNet regression · CTSliceRMSE: 1.45 -> 1.09Improved
replace STE with annealed Top-k selection (ablation)DTSemNet regression · PolRMSE: 7.62 -> 6.61Improved
replace STE with annealed Top-k selection (ablation)DTSemNet regression · Comp-ActiveRMSE: 2.65 -> 2.48Improved
replace STE with annealed Top-k selection (ablation)DTSemNet regression · PDBBindRMSE: 1.34 -> 1.33No clear effect
replace STE with annealed Top-k selection (ablation)DTSemNet regression · Regression Table 1 averageavg % distance to best: 8.8% -> 0.6%Improved
update top-k regressors instead of only one (Top-4 vs Top-4/Reg-1) (ablation)DTSemNet Top-k · CTSlice leaf utilization after epoch 1regressors with >100 samples: 16 -> 22Improved
update internal nodes with only top-k leaves instead of all leaves (Top-4/Reg-1 vs STE, end of training) (ablation)DTSemNet Top-k · CTSlice leaf utilization at endregressors used: 8 -> 15Improved
update top-k regressors and use top-k routing (Top-4 vs STE, end of training) (ablation)DTSemNet · CTSlice leaf utilization at endregressors with >180 samples: 8 -> 20Improved
use Top-2 instead of STE to learn the root weight with other nodes frozen (ablation)DTSemNet · synthetic teacher-student root weightconvergence to teacher weightImproved
replace DGT's STE architecture with DTSemNetDGT · Dry Beanaccuracy: 89.0 -> 91.4Improved
replace DGT with DTSemNetDGT · MNIST (height 8)accuracy: 94.00 -> 96.16Improved
replace DGT with DTSemNetDGT · Letter (height 10)accuracy: 86.13 -> 89.19Improved

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