Papers › Probabilistic Autoencoder

Probabilistic Autoencoder

9 Jun 2020Under review 2020 6arXiv:2006.05479archive 2025-07-28

Vanessa Böhm, Uroš Seljak

Principal Component Analysis (PCA) minimizes the reconstruction error given a class of linear models of fixed component dimensionality. Probabilistic PCA adds a probabilistic structure by learning the probability distribution of the PCA latent space weights, thus creating a generative model. Autoencoders (AE) minimize the reconstruction error in a class of nonlinear models of fixed latent space dimensionality and outperform PCA at fixed dimensionality. Here, we introduce the Probabilistic Autoencoder (PAE) that learns the probability distribution of the AE latent space weights using a normalizing flow (NF). The PAE is fast and easy to train and achieves small reconstruction errors, high sample quality, and good performance in downstream tasks. We compare the PAE to Variational AE (VAE), showing that the PAE trains faster, reaches a lower reconstruction error, and produces good sample quality without requiring special tuning parameters or training procedures. We further demonstrate that the PAE is a powerful model for performing the downstream tasks of probabilistic image reconstruction in the context of Bayesian inference of inverse problems for inpainting and denoising applications. Finally, we identify latent space density from NF as a promising outlier detection metric.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2006.05479")

Code

Syntology Ran 1 of 13 code samples harvested from 2 repositories linked to this paper; 12 have no recorded run. Of those that ran: 1 ran · our draft was wrong.

By repository: official repository: 12 samples from 1 repository, 0 ran; community (archive-listed): 1 sample from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

VMBoehm/PAE officialmentioned in papermentioned on GitHubtfGPL-3.0 report
vmboehm/pae-ablation officialmentioned in papermentioned on GitHubtfApache-2.0 report
AI-for-Ocean-Science/ulmo mentioned on GitHubpytorch report
chrvt/denoising-normalizing-flow mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

13 samples harvested; 1 ran; 0 honoured the contract we drafted; 12 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · our draft was wrong
12unverified

Licence: 0 of the 13 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

conv2d vmboehm/pae-ablation/pae/util_2stageVAE_tf2.py official repository unverified Apache-2.0 (permissive) · 7600fd868e849534 · report
dequantize vmboehm/pae-ablation/pae/create_datasets_tf2.py official repository unverified Apache-2.0 (permissive) · 599a4b97af909541 · report
get_GN_covariance vmboehm/pae-ablation/pae/model_tf2.py official repository unverified Apache-2.0 (permissive) · a4af2f55127481cb · report
init_once vmboehm/pae-ablation/pae/flow_tf2.py official repository unverified Apache-2.0 (permissive) · 43ef698514227548 · report
linear vmboehm/pae-ablation/pae/util_2stageVAE_tf2.py official repository unverified Apache-2.0 (permissive) · 60f7837af07944ce · report
make_images vmboehm/pae-ablation/pae/model_tf2.py official repository unverified Apache-2.0 (permissive) · b7596b739149d93a · report
res_block vmboehm/pae-ablation/pae/networks_tf2.py official repository unverified Apache-2.0 (permissive) · aabec1271ea64e72 · report
res_fc_block vmboehm/pae-ablation/pae/networks_tf2.py official repository unverified Apache-2.0 (permissive) · e0d965c835d230b6 · report
residual_op vmboehm/pae-ablation/AbatiComparison/models.py official repository unverified Apache-2.0 (permissive) · e0fab0d1e7d95d7b · report
scale_block vmboehm/pae-ablation/pae/networks_tf2.py official repository unverified Apache-2.0 (permissive) · 0a6044204c031491 · report
spectral_norm vmboehm/pae-ablation/pae/util_2stageVAE_tf2.py official repository unverified Apache-2.0 (permissive) · 241e498a062673bc · report
trainable_lu_factorization vmboehm/pae-ablation/pae/flow_tf2.py official repository unverified Apache-2.0 (permissive) · 95096c3ee1dfee33 · report
integrand_circle chrvt/denoising-normalizing-flow/experiments/evaluate.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 69ee46a945fa4d1a · report

Tasks

Bayesian InferenceDenoisingImage GenerationImage ReconstructionOut-of-Distribution DetectionOutlier DetectionUnsupervised Anomaly Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image Generation CelebA 64x64 PAE FID 49.2 #34 of 39 Archive leaderboard report
Image Generation Fashion-MNIST PAE FID 28.0 #4 of 7 Archive leaderboard report
Out-of-Distribution Detection Fashion-MNIST PAE AUROC 0.997 #1 of 2 Archive leaderboard report
Outlier Detection Fashion-MNIST PAE AUROC 0.997 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections