AI Paper Atlas

Research map / Learning theory and algorithms / Sample complexity

Testing Probabilistic Circuits

Yash Pote, Kuldeep S. Meel

NeurIPS 2021 · Learning theory and algorithms › Sample complexity · approach: Generalization and limits under data constraints · 0 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
Run Teq on random 3-CNF pairs with 14-18 variables, checking against brute-force TV distanceTeq · Synthetic 3-CNF (375 PCs)correctness / runtime: less than 10 secondsImproved
Run Teq on pairs of d-DNNF circuits with one-variable-perturbed weightsTeq · Real-world d-DNNF benchmarks (100 PCs)correctness / runtime: less than 3600 secondsImproved
Eta-far input pair instead of eps-close pairTeq · Real-world d-DNNF benchmarksruntime (s): 414.17 -> 408.59No clear effect
Eta-far input pair instead of eps-close pairTeq · s1423a_7_4runtime (s): 104.93 -> 103.51No clear effect
Choose eps=0.01, eta=0.2, delta=0.01 so that sample count depends only on these parametersTeq · Real-world d-DNNF benchmarkssamples required: m=294Improved
Larger circuits (e.g. or-50-5-4, ProjectService3) versus smaller ones (or-70-10-8-UC-10)Teq · Real-world d-DNNF benchmarksruntime (s): 23.2 -> 414.17Hurt
Pair with actual TV 0.804 lying between eps and etaTeq · Synthetic 3-CNF 15_3decisionNo clear effect

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