AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

On the Probabilistic Learnability of Compact Neural Network Preimage Bounds

Luca Marzari, Manuele Bicego, Ferdinando Cicalese, Alessandro Farinelli

AAAI 2026 · Learning theory and algorithms › Combinatorial and search optimization · approach: Semidefinite relaxations for verification · 2 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
add active resampling filtering phase (ablation)RF-ProVe · Lunarlanderimpurity (% error): 3.54% -> 0.3%Improved
add active resampling filtering phase (ablation)RF-ProVe · Lunarlandernumber of polytopes: 190 -> 42Improved
add active resampling filtering phase (ablation)RF-ProVe · Dubinsrejoinnumber of polytopes: 308 -> 136Improved
add active resampling filtering phase (ablation)RF-ProVe · RL tasksruntime: 20s -> 59sHurt
use random-forest ensemble instead of single tree (eps-ProVe)preimage approximation · Dubinsrejoinnumber of polytopes: 4929 -> 136Improved
use RF-ProVe instead of PREMAPpreimage approximation · VCASruntime: 12.8s -> 0.3sImproved
use RF-ProVe instead of PREMAPpreimage approximation · Cartpoleruntime: 32.37s -> 4.5sImproved
use RF-ProVe instead of sound PREMAPpreimage approximation · Lunarlanderimpurity (% error): 0% -> 0.3%Hurt
use RF-ProVe instead of exact methodpreimage approximation · VCASruntime: 6352.21s -> 0.3sImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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