AI Paper Atlas

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

Arbitrary Conditional Distributions with Energy

Ryan Strauss, Junier Oliva

NeurIPS 2021 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Likelihood-free and graphical model estimation · 1 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 energy network likelihood instead of proposal-only likelihood (ablation)ACE · UCI Power, missing rate 0.0conditional log-likelihood: 0.583 -> 0.631Improved
use energy network likelihood instead of proposal-only likelihood (ablation)ACE · UCI Gas, missing rate 0.0conditional log-likelihood: 9.484 -> 9.643Improved
use energy network likelihood instead of proposal-only likelihood (ablation)ACE · UCI Hepmass, missing rate 0.0conditional log-likelihood: -4.417 -> -3.859Improved
use energy network likelihood instead of proposal-only likelihood (ablation)ACE · UCI Miniboone, missing rate 0.5conditional log-likelihood: -9.169 -> -5.701Improved
use energy network likelihood instead of proposal-only likelihood (ablation)ACE · UCI BSDS, missing rate 0.5conditional log-likelihood: 75.767 -> 80.613Improved
replace ACFlow with ACE proposal network (fully-connected, mixture of Gaussians)conditional density model · UCI Gas, missing rate 0.0conditional log-likelihood: 8.086 -> 9.484Improved
replace ACFlow with ACEconditional density model · UCI Hepmass, missing rate 0.0conditional log-likelihood: -8.197 -> -3.859Improved
replace VAEAC with ACEconditional density model · UCI Power, missing rate 0.0conditional log-likelihood: -0.042 -> 0.631Improved
increase training missing rate from 0.0 to 0.5ACE · UCI Hepmassconditional log-likelihood: -3.859 -> -8.133Hurt
replace ACFlow with ACEarbitrary marginal estimation · UCI Miniboone, marginal over 10 dimsmarginal log-likelihood: -10.36 -> -7.94Improved
compare ACE with TAN trained per marginalACE · UCI BSDS, marginal over 10 dimsmarginal log-likelihood: 20.31 vs 20.44No clear effect
consistency fine-tuning with variance coefficient 2.0 instead of 0.0 (ablation)ACE · UCI Hepmassconditional log-likelihood: -3.555 -> -4.090Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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