Research map / Learning theory and algorithms / Sample complexity
Testing Probabilistic Circuits
Yash Pote, Kuldeep S. Meel
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Run Teq on random 3-CNF pairs with 14-18 variables, checking against brute-force TV distance | Teq · Synthetic 3-CNF (375 PCs) | correctness / runtime: less than 10 seconds | Improved |
| Run Teq on pairs of d-DNNF circuits with one-variable-perturbed weights | Teq · Real-world d-DNNF benchmarks (100 PCs) | correctness / runtime: less than 3600 seconds | Improved |
| Eta-far input pair instead of eps-close pair | Teq · Real-world d-DNNF benchmarks | runtime (s): 414.17 -> 408.59 | No clear effect |
| Eta-far input pair instead of eps-close pair | Teq · s1423a_7_4 | runtime (s): 104.93 -> 103.51 | No clear effect |
| Choose eps=0.01, eta=0.2, delta=0.01 so that sample count depends only on these parameters | Teq · Real-world d-DNNF benchmarks | samples required: m=294 | Improved |
| Larger circuits (e.g. or-50-5-4, ProjectService3) versus smaller ones (or-70-10-8-UC-10) | Teq · Real-world d-DNNF benchmarks | runtime (s): 23.2 -> 414.17 | Hurt |
| Pair with actual TV 0.804 lying between eps and eta | Teq · Synthetic 3-CNF 15_3 | decision | No clear effect |
Closest papers by meaning
- Probabilistic Neural Circuits (AAAI 2024 · similarity 0.88)
- On the Hardness of Approximating Distributions with Tractable Probabilistic Models (NeurIPS 2025 · similarity 0.87)
- Scaling Probabilistic Circuits via Monarch Matrices (ICML 2025 · similarity 0.87)
- On the Expressive Power of Tree-Structured Probabilistic Circuits (NeurIPS 2024 · similarity 0.87)
- Sum of Squares Circuits (AAAI 2025 · similarity 0.85)
- On the Relationship Between Monotone and Squared Probabilistic Circuits (AAAI 2025 · similarity 0.85)
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.
