Research map / Probabilistic and scientific modeling / Variational and generative sampling
The Sum-Product Theorem: A Foundation for Learning Tractable Models
Abram Friesen, Pedro Domingos
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 |
|---|---|---|---|
| Add decomposability (disjoint scopes of product factors) as the enforced learning constraint for SPFs in LearnSPF | nonconvex min-sum function learning · Rastrigin-based nonconvex function, 4-to-many variables | minimum found when optimizing learned function under fixed time budget | Improved |
| Decomposable SPF summation vs. no decomposition constraint in learned model | SPN/SPF inference · theory (sum-product theorem) | tractability | Improved |
| Require completeness in addition to decomposability for SPNs | sum-product networks · theory | tractability condition | No clear effect |
Closest papers by meaning
- Maximum A Posteriori Inference in Sum-Product Networks (AAAI 2018 · similarity 0.90)
- Collapsed Variational Inference for Sum-Product Networks (ICML 2016 · similarity 0.89)
- Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs (ICLR 2024 · similarity 0.87)
- Position: A Theory of Deep Learning Must Include Compositional Sparsity (ICML 2025 · similarity 0.86)
- Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks (ICLR 2024 · similarity 0.86)
- Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks (ICLR 2024 · similarity 0.86)
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.
