AI Paper Atlas

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

Fast and Functional Structured Data Generators Rooted in Out-of-Equilibrium Physics

Alessandra Carbone, Aurélien Decelle, Lorenzo Rosset, Beatriz Seoane

TPAMI 2024 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Sequential Monte Carlo for inference · 12 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
train with 10 out-of-equilibrium MCMC steps (F&F-10) instead of persistent chains with 100 steps (PCD-100)RBM conditional generator · MNIST and GH30generation quality scoresImproved
use F&F-10 training instead of PCD-100RBM · SAM RNAsampling steps to cover all classes: 10 -> 10^5 MCMC stepsImproved
use F&F-10 training instead of PCD-100RBM · all datasetstraining timeImproved
train F&F with F&F vs PCD on label classificationRBM · five labelled datasetslabel prediction accuracyNo clear effect
add second label-prediction gradient to the conditional generation gradient (ablation)F&F RBM · five labelled datasetslabel prediction accuracyImproved
change number of hidden nodes (100 vs 1000) under PCD-100 (ablation)PCD-100 RBM · SAMgeneration qualityHurt

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