AI Paper Atlas

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

Provable Explanations for Any-Order Neural Additive Models

Idan Refaeli, Shahaf Bassan, Yizhak Y. Elboher, Guy Katz

NeurIPS 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Provable post-hoc explanations

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes provably sufficient, cardinally minimal feature explanations for any-order neural additive models, building on tractable explanations for neural additive models.

Problem

Post-hoc explanations for neural networks are heuristic; computing cardinally minimal provably sufficient feature subsets is intractable for general neural networks.

Approach

Extends tractable provable explanations from neural additive models to any-order neural additive models, which allow feature interactions while keeping explanation computation tractable. Full method details are not available in the provided text.

Experimental setup

Builds on: neural additive models

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