AI Paper Atlas

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

Monte Carlo Variational Auto-Encoders

Achille Thin, Nikita Kotelevskii, Arnaud Doucet, Alain Durmus, Eric Moulines, Maxim Panov

ICML 2021 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Sequential Monte Carlo for inference · 10 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 L-MCVAE with Langevin SIS transitions instead of VAEVAE · CelebA, 100 epochsNLL estimate: 10.11 ± 0.32 -> 8.24 ± 0.52Improved
Use L-MCVAE with Langevin SIS transitions instead of VAEVAE · CIFAR-10, 100 epochsNLL estimate: 67.9 ± 0.03 -> 67.5 ± 0.07Improved
Use L-MCVAE with Langevin SIS transitions instead of VAEVAE · MNIST, 100 epochsNLL estimate: 85.22 ± 0.07 -> 84.58 ± 0.39Mixed
Increase Langevin transition steps (ablation)L-MCVAE · MNIST, CIFAR-10, and CelebANLL estimate: MNIST, K=5: 84.92 ± 0.24 -> K=10: 84.58 ± 0.39; CelebA, K=5: 8.72 ± 0.4 -> K=10: 8.24 ± 0.52; CIFAR-10, K=5: 67.5 ± 0.07Mixed
Use AIS-based A-MCVAE instead of L-MCVAEMonte Carlo VAE · Probabilistic PCA on MNISTELBO tightnessMixed
Add control variates to the A-MCVAE gradient estimator (ablation)A-MCVAE · Probabilistic PCA on MNISTgradient varianceImproved
Use learned neural backward kernels instead of approximate reversal kernels (ablation)L-MCVAE · Probabilistic PCA on MNISTestimator varianceHurt
Use learned neural backward kernels instead of approximate reversal kernels (ablation)L-MCVAE · Probabilistic PCA on MNISTgradient varianceHurt
Increase the number of Langevin steps (ablation)L-MCVAE · MNIST trainingheld-out loglikelihoodImproved
Use learned rather than fixed temperatures (ablation)L-MCVAE and A-MCVAE · MNIST, CelebA, and CIFAR-10NLL estimateMixed

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