AI Paper Atlas

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

Gauging Variational Inference

Sung-Soo Ahn, Michael Chertkov, Jinwoo Shin

NeurIPS 2017 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Annealing and divergence-based variational objectives · 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
Optimize gauges jointly with the product distributionMean-field · Generic graphical modelslower bound on log partition functionImproved
Constrain gauge-transformed factors to be nonnegativeBelief propagation gauge optimization · General graphical modelslower bound on log partition functionImproved
Apply Gauged-BP sequentially to residual partition functions (ablation)Gauged-BP · Complete graphical modelslog-partition approximation errorImproved
Include multiple configurations differing from the all-zero configuration (ablation)Gauged-BP · Complete graphical modelslog-partition approximation errorImproved
Use sequential residual-partition correction (ablation)Gauged-BP · Large generic non-log-supermodular graphslog(Z_LB/Z_MF): up-to e^{14} timesImproved
Use Gauged-BP-based algorithmsMean-field and Gauged-MF · Large log-supermodular graphslog(Z_LB/Z_MF): up to e^{25} timesImproved
Fix the product distribution to the all-zero configuration rather than optimizing it (ablation)Gauged-MF · General graphical modelslower bound on log partition functionHurt
Use the all-zero configuration as the fixed distribution (ablation)Gauged-MF · Log-supermodular modelslog(Z_LB/Z_MF)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