AI Paper Atlas

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

Evidence Estimation in Gaussian Graphical Models Using a Telescoping Block Decomposition of the Precision Matrix

Anindya Bhadra, Ksheera Sagar, David Rowe, Sayantan Banerjee, Jyotishka Datta

JMLR 2024 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Likelihood-free and graphical model estimation · 2 citations (OpenAlex)

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 the telescoping-block Chib-style estimator instead of AIS and nested samplingproposed estimator · Wishart priorlog marginal estimate: AIS -397.64 vs proposed -365.1 at truth -365.11 (p=10)Improved
Use the proposed estimator instead of the harmonic meanproposed estimator · Wishart priorlog marginal estimate: -345.47 -> -365.1 (truth -365.11)Improved
Use proposed estimator instead of AIS in large dimensionsproposed estimator · Wishart prior p>=25log marginal estimate: -infinity for AIS vs -2416.83 (p=25)Improved
Use proposed estimator instead of nested sampling in large dimensionsproposed estimator · Bayesian graphical lasso p>=15log marginal estimate: -infinity for nested vs -796.66 (p=15)Improved
Use proposed estimator on graphical horseshoe at p=2, lambda=1, n=5proposed estimator · Graphical horseshoelog marginal estimate: -20.11 truth: proposed -20.08, AIS -20.38, HM -19.54Improved
Use proposed estimator at p=5 on graphical horseshoeproposed estimator · Graphical horseshoelog marginal estimate: -60.05 vs AIS -54.93, nested -55.27, HM -53.45 (no truth known)Hurt
Use proposed estimator on Bayesian graphical lasso at p=2, lambda=0.4, n=4proposed estimator · Bayesian graphical lassolog marginal estimate: -12.33 truth: proposed -12.33 (0.00), HM -12.03 (0.43)Improved

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