AI Paper Atlas

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

Beyond Additive Decompositions: Interpretability Through Separability

Jinyang Liu, Munir Hiabu

ICML 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Provable post-hoc explanations · 0 citations (OpenAlex)

Read the paper

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
remove positivity constraint and ordered-difference structure (TSL 1-product, R<=4) vs TSL R<=2 (ablation)TSL · socmobRMSE: 10.58 -> 9.87Improved
add positivity and ordered-difference structure vs TSL 1-product (ablation)TSL · naval propulsion plantRMSE: 0.0027 -> 0.0013Improved
add positivity and ordered-difference structure vs TSL 1-product (ablation)TSL · auction verificationRMSE: 1336.51 -> 1135.80Improved
TSL R<=10 vs additive EBMTSL · socmobRMSE: 20.21 -> 9.48Improved
TSL R<=2 vs SepALS (r<=2) with fixed basis, matched rankTSL · california housingRMSE: 62162.22 -> 49376.09Improved
TSL vs EBM on largely additive problemsTSL · red wineRMSE: 0.5991 -> 0.6438Hurt
TSL vs SepALSTSL · naval propulsion plant, forest fires, kin8nm, energy efficiency, grid stabilityRMSEHurt
TSL R<=10 vs depth-2 interpretable XGBoostTSL · brazilian housesRMSE: 2528.95 -> 2398.68Improved
TSL R<=10 vs black-box XGBoostTSL · miami housingRMSE: 89692.96 vs 82325.09Hurt

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