AI Paper Atlas

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

Scalable Interpretability via Polynomials

Abhimanyu Dubey, Filip Radenovic, Dhruv Mahajan

NeurIPS 2022 · Learning theory and algorithms › Prediction and decision losses · approach: Theory of neural network sensitivity · 9 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 SPAM-Neural with 8 subnets instead of the original SPAM-Neural configuration (ablation)SPAM-Neural · Cover Type (CovType)Accuracy: 0.8857 -> 0.9405Improved
Increase interaction degree beyond 3 (ablation)SPAM · CoverType and iNaturalist BirdsAccuracyImproved
Increase cumulative rank (ablation)SPAM · 20 Newsgroups and iNaturalist BirdsAccuracyNo clear effect
Use L1 sparsity on basis vectors, retaining only 6% of possible pairwise interactions (ablation)SPAM (degree 2, rank 800) · CUB-200Accuracy: 6%No clear effect
Use pairwise interactions rather than unary-only termsSPAM · CUB-200Accuracy: 0.7451 -> 0.7786Improved
Use pairwise interactions rather than unary-only termsSPAM · 20 NewsgroupsAccuracy: 0.8238 -> 0.8472Improved
Use pairwise interactions rather than unary-only termsSPAM · iNaturalist BirdsAccuracy: 0.3932 -> 0.4605Improved
Use pairwise interactions rather than unary-only termsSPAM · CO114mAP: 0.1917 -> 0.2361Improved
Show SPAM explanations instead of LIME explanationsCUB-200 explanation prediction task · CUB-200Mean user accuracy: 0.65 -> 0.71Improved
Increase explanation length beyond 7 terms (ablation)SPAM-Linear (Order 2) and LIME explanations · CUB-200 explanation prediction taskMean user accuracyHurt

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