Research map / Probabilistic and scientific modeling / Variational and generative sampling
Fast and Flexible Inference of Joint Distributions from their Marginals
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use a Normal prior with perfectly observed marginals instead of independence | joint table inference · DEATH, EDUCATION, INCOME, INSURANCE (Table 1) | median absolute error | Helped |
| Replace Goodman regression with MAP-based models | joint table inference · DEATH, INSURANCE | median absolute error | Helped |
| Entropic prior with perfectly observed marginals | joint table inference · EDUCATION | median absolute error | Helped |
| Tsallis prior and Dirichlet prior vary in performance across datasets | perfect-marginal MAP models · all five datasets | median absolute error | Mixed |
| Replace MCMC multinomial-Dirichlet inference with the proposed MAP inference | joint table inference (computation) · runtime, 100 tables | runtime factor: roughly a factor of three faster | Helped |
| Replace TROT with the proposed MAP inference for Tsallis models | Tsallis perfect-marginal models · runtime, table sizes up to 64x64 | runtime: between one and two orders of magnitude faster | Helped |
| Use multinomial observations for both marginals instead of perfect marginals | MAP inference runtime · runtime, 100 tables | runtime | Hurt |
Closest papers by meaning
- Relational Marginal Problems: Theory and Estimation (AAAI 2018 · similarity 0.85)
- QuEst: Enhancing Estimates of Quantile-Based Distributional Measures Using Model Predictions (ICML 2025 · similarity 0.83)
- The Limits of Inference Scaling Through Resampling (ICLR 2026 · similarity 0.83)
- Valid Inference with Imperfect Synthetic Data (NeurIPS 2025 · similarity 0.83)
- Exploiting LLMs for Automatic Hypothesis Assessment via a Logit-Based Calibrated Prior (NeurIPS 2025 · similarity 0.82)
- Marginal Causal Flows for Validation and Inference (NeurIPS 2024 · similarity 0.82)
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.