Research map / Probabilistic and scientific modeling / Variational and generative sampling
Exact Inference for Integer Latent-Variable Models
Kevin Winner, Debora Sujono, Dan Sheldon
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 |
|---|---|---|---|
| use GDUAL-FORWARD instead of truncated forward algorithm TRUNC | Poisson HMM likelihood · running time vs Y, rho=0.15 | running time: about 8x faster | Improved |
| use GDUAL-FORWARD instead of TRUNC | Poisson HMM likelihood · running time vs Y, rho=0.85 | running time: 2x faster | Improved |
| use PGF-FORWARD instead of GDUAL-FORWARD | Poisson HMM likelihood · running time | running time | Improved |
| increase detection probability rho from 0.05 to 0.95 | GDUAL-FORWARD and PGF-FORWARD · PHMM, PHMM-peaked, NMix | running time | Hurt |
| increase detection probability rho | TRUNC with oracle Nmax · PHMM, PHMM-peaked, NMix | running time | Improved |
| NMix model (immigration only at first step) versus other models | GDUAL-FORWARD relative to PGF-FORWARD · NMix | running time | Improved |
| use GDUAL-FORWARD within MLE for varied immigration and offspring distributions | L-BFGS-B parameter estimation · Estimates of R, 0.2 to 1.2 | estimate of R | Improved |
Closest papers by meaning
- Probabilistic Inference with Generating Functions for Poisson Latent Variable Models (NeurIPS 2016 · similarity 0.91)
- Exact Bayesian Inference on Discrete Models via Probability Generating Functions: A Probabilistic Programming Approach (NeurIPS 2023 · similarity 0.85)
- Graphical model inference: Sequential Monte Carlo meets deterministic approximations (NeurIPS 2018 · similarity 0.85)
- On the Identifiability of Poisson Branching Structural Causal Model Using Probability Generating Function (NeurIPS 2024 · similarity 0.83)
- A Generic Family of Graphical Models: Diversity, Efficiency, and Heterogeneity (ICML 2025 · similarity 0.83)
- Causal Discovery from Poisson Branching Structural Causal Model Using High-Order Cumulant with Path Analysis (AAAI 2024 · similarity 0.83)
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.
