AI Paper Atlas

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

Learning outside the Black-Box: The pursuit of interpretable models

Jonathan Crabbe, Yao Zhang, William Zame, Mihaela van der Schaar

NeurIPS 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Provable post-hoc explanations · 13 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
Use Symbolic Pursuit instead of LIME to estimate feature importanceSynthetic linear model · Synthetic linear modelsquared importance error: 0.66 ± 0.07 -> 0.02 ± 0.05Improved
Use Symbolic Pursuit instead of SHAP to estimate feature importanceSynthetic linear model · Synthetic linear modelsquared importance error: 0.66 ± 0.07 -> 0.02 ± 0.05Improved
Fit a Symbolic Pursuit model to approximate the black-boxMLP · Wine, Yacht, Boston, Energy, ConcreteR² vs black-boxImproved
Fit a Symbolic Pursuit model to approximate the black-boxSVM · Wine, Yacht, Boston, Energy, ConcreteR² vs black-boxImproved

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