AI Paper Atlas

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

MIWAE: Deep Generative Modelling and Imputation of Incomplete Data Sets

Pierre-Alexandre Mattei, Jes Frellsen

ICML 2019 · Probabilistic and scientific modeling › Variational and generative sampling · approach: Tractable probabilistic models · 112 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 MIWAE multiple imputation instead of complete training dataConvolutional classifier · MNIST static binarisation, 50% pixels missingTest accuracy: 0.9866 (0.0007) -> 0.9868 (0.0008)Improved
Use MIWAE multiple imputation instead of complete training dataConvolutional classifier · MNIST static binarisation, 50% pixels missingTest cross-entropy: 0.0464 (0.0026) -> 0.0509 (0.0044)Hurt
Use MIWAE single imputation instead of missForest imputationConvolutional classifier · MNIST static binarisation, 50% pixels missingTest accuracy: 0.9805 (0.0018) -> 0.9847 (0.0009)Improved
Use MIWAE single imputation instead of missForest imputationConvolutional classifier · MNIST static binarisation, 50% pixels missingTest cross-entropy: 0.0645 (0.0066) -> 0.0510 (0.0035)Improved
Use MIWAE with K=20 instead of MVAE with K=1 (ablation)MIWAE single imputation · BanknoteMean-squared error: 0.593 (0.059) -> 0.446 (0.038)Improved
Use MIWAE with K=20 instead of MVAE with K=1 (ablation)MIWAE single imputation · BreastMean-squared error: 0.318 (0.018) -> 0.280 (0.021)Improved
Use MIWAE with K=20 instead of MVAE with K=1 (ablation)MIWAE single imputation · ConcreteMean-squared error: 0.587(0.026) -> 0.501 (0.040)Improved
Use MIWAE with K=20 instead of MVAE with K=1 (ablation)MIWAE single imputation · RedMean-squared error: 0.686 (0.120) -> 0.643 (0.026)Improved
Use MIWAE with K=20 instead of MVAE with K=1 (ablation)MIWAE single imputation · WhiteMean-squared error: 0.782 (0.018) -> 0.735 (0.033)Improved
Use MIWAE with K=20 instead of MVAE with K=1 (ablation)MIWAE single imputation · YeastMean-squared error: 0.997 (0.064) -> 0.964(0.057)Improved
Use zero imputation instead of oracle imputation during training (ablation)MIWAE with K=50 · MNIST static binarisation, 50% pixels missingTest log-likelihoodNo clear effect
Use zero imputation instead of oracle imputation during training (ablation)MVAE with K=1 · MNIST static binarisation, 50% pixels missingTest log-likelihoodHurt

Later papers that compared with this method

4 later accepted papers report MIWAE as a baseline in their results tables; 3 of them report a better number on most of the results they share with it.

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