AI Paper Atlas

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

Ancestral Gumbel-Top-k Sampling for Sampling Without Replacement

Wouter Kool, Herke van Hoof, Max Welling

JMLR 2020 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Sequential Monte Carlo for inference · 18 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 ancestral Gumbel-Top-k sampling instead of rejection or naive ancestral sampling without replacementsampling without replacement from Bayesian network · Random Bayesian networks (10 Bernoulli variables)model evaluations: fewest iterations/model evaluations to generate the same number of samplesImproved
increase parallel processors m from 1 to 100 (ablation)ancestral Gumbel-Top-k sampling · Random Bayesian network (c=0.5, k=100)iterations vs total cost: around 300 iterations (cost 300) -> 10 iterations (cost 1000)Mixed
limited parallelism m = 10 (ablation)ancestral Gumbel-Top-k sampling · Random Bayesian network (c=0.5, k=100)iterations vs total costImproved
select next variable by minimum entropy instead of fixed or random order (ablation)ancestral Gumbel-Top-k sampling (m=1) · Random Bayesian networks, k=100iterationsImproved
use Stochastic Beam Search instead of Diverse Beam Searchdiverse translation sets · WMT14 En-Fr newstest2014 (k=5,10,20)mean/maximum BLEU at equal diversityImproved
use Stochastic Beam Search instead of Sampling with replacementdiverse translation sets · WMT14 En-Fr newstest2014 (k=5,10,20)mean BLEU and diversityMixed
use normalized SBS estimator instead of unnormalized SBS (ablation)sentence BLEU estimation · WMT14 En-Fr, three sentencesestimator varianceImproved
use normalized SBS estimator instead of Monte Carlosentence BLEU estimation · WMT14 En-Fr, three sentences (τ < 0.5)estimator varianceImproved
use normalized SBS estimator instead of Monte Carlo at higher temperaturesentence BLEU estimation · WMT14 En-Fr, τ = 0.5estimator varianceNo clear effect
use normalized SBS estimator instead of Monte Carlo for entropyconditional entropy estimation · WMT14 En-Fr, τ < 0.5estimator varianceImproved

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