AI Paper Atlas

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

Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delay

Joao Marques-Silva, Thomas Gerspacher, Martin Cooper, Alexey Ignatiev, Nina Narodytska

NeurIPS 2020 · Learning theory and algorithms › Prediction and decision losses · approach: Provable post-hoc explanations

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 XPXLC's direct PI-explanation enumeration instead of STEP's SDD enumerationNaive Bayes Classifiers · NBC classifiers compilable within 2 hoursPI-explanation enumeration runtime: between 4 and 20 times slower than XPXLCImproved
Use XPXLC instead of Anchor for instance-level explanation generationNaive Bayes Classifiers · Instance-level explanation generationruntime: Anchor takes 1.55 seconds; XPXLC never exceeds a few tens of μsecImproved
Use XPXLC instead of SHAP for instance-level explanation generationNaive Bayes Classifiers · Instance-level explanation generationruntime: SHAP takes 99.58 seconds; XPXLC never exceeds a few tens of μsecImproved
Use heuristic feature explanations rather than the most common features in enumerated PI-explanationsAnchor and SHAP · Adult and Spambaseoverlap with common PI-explanation features: Anchor has zero overlap in more than 2000 instancesMixed

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