AI Paper Atlas

Research map / Probabilistic and scientific modeling / Variational and generative sampling

Measuring Sample Quality in Algorithms for Intractable Normalizing Function Problems

Bokgyeong Kang, John Hughes, Murali Haran

JMLR 2024 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Importance sampling and quadrature

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
use IMQ KSD instead of curvature diagnosticmultivariate normality test · p=25, n=1000Type I error rate: 0.13 -> 0.00Improved
increase sample size from 1000 to 5000curvature diagnostic · p=25Type I error rate: 0.13 -> 0.02Improved
compare CD and KSD powermultivariate normality test · n=1000..5000, p=2..25power: 1 for bothNo clear effect
select d by ACD/AIKS instead of ESSAEX on Ising model · Ising 30x30, theta=0.2tuning choice: d=100 -> d=470Improved
use ACD/AIKS-recommended m=4 instead of ESS-best m=1DMH on Ising model · Ising 30x30right-tail probability: 0.09 -> 0.05Improved
use truncation k=10 instead of ESS-best k=3NormTrunc on COM-Poisson · COM-Poisson regression beta_0median: 0.45 -> 0.31Improved
use truncation k=10 instead of k=3NormTrunc on COM-Poisson · COM-Poisson regression beta_0right-tail probability: 0.47 -> 0.05Improved
add more particles d for ALRALR on Ising model · Ising 30x30diagnosticsNo clear effect
use ACD instead of AIKS for large ndiagnostic cost · Ising modelcomputation time: 27 seconds -> 3 secondsImproved

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