Papers › Gaussianization Flows

Gaussianization Flows

4 Mar 2020arXiv:2003.01941archive 2025-07-28

Chenlin Meng, Yang song, Jiaming Song, Stefano Ermon

Iterative Gaussianization is a fixed-point iteration procedure that can transform any continuous random vector into a Gaussian one. Based on iterative Gaussianization, we propose a new type of normalizing flow model that enables both efficient computation of likelihoods and efficient inversion for sample generation. We demonstrate that these models, named Gaussianization flows, are universal approximators for continuous probability distributions under some regularity conditions. Because of this guaranteed expressivity, they can capture multimodal target distributions without compromising the efficiency of sample generation. Experimentally, we show that Gaussianization flows achieve better or comparable performance on several tabular datasets compared to other efficiently invertible flow models such as Real NVP, Glow and FFJORD. In particular, Gaussianization flows are easier to initialize, demonstrate better robustness with respect to different transformations of the training data, and generalize better on small training sets.

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="2003.01941")

Code

Syntology Ran 1 of 21 code samples harvested from 3 repositories linked to this paper; 20 have no recorded run. Of those that ran: 1 ran · fixture could not drive it.

By repository: official repository: 1 sample from 1 repository, 1 ran; community (archive-listed): 20 samples from 2 repositories, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

chenlin9/Gaussianization_Flows officialmentioned 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

21 samples harvested; 1 ran; 0 honoured the contract we drafted; 20 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 · fixture could not drive it
20unverified

Licence: 1 of the 21 samples is 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 3 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.

flow_loss chenlin9/Gaussianization_Flows/tabular_experiment.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · d29ea21629f4ac1b · report
add_wandb_args IPL-UV/gaussflow/src/experiments/utils.py community (archive-listed) unverified MIT (permissive) · 5d04f997a7a2e253 · report
conv_exp IPL-UV/gaussflow/src/models/linear.py community (archive-listed) unverified MIT (permissive) · 93b57317942866eb · report
generate_2d_grid IPL-UV/gaussflow/src/viz/bivariate.py community (archive-listed) unverified MIT (permissive) · e8bea811f4c19c70 · report
get_quantiles IPL-UV/rbig_jax/rbig_jax/quantiles.py community (archive-listed) unverified MIT (permissive) · c7f37f093738dc31 · report
info_red_cond IPL-UV/rbig_jax/rbig_jax/stopping.py community (archive-listed) unverified MIT (permissive) · dfd3476c2058eb71 · report
init_train_op IPL-UV/rbig_jax/rbig_jax/training_old.py community (archive-listed) unverified MIT (permissive) · f6023901bf40e193 · report
marginal_transform IPL-UV/rbig_jax/rbig_jax/utils.py community (archive-listed) unverified MIT (permissive) · 5b1d0013e3b6ee41 · report
matrix_exp IPL-UV/gaussflow/src/models/linear.py community (archive-listed) unverified MIT (permissive) · 47b5ae77e59c4063 · report
matrix_log IPL-UV/gaussflow/src/models/linear.py community (archive-listed) unverified MIT (permissive) · 4e907657e24742b5 · report
negative_log_likelihood_bpd IPL-UV/gaussflow/src/losses/nll.py community (archive-listed) unverified MIT (permissive) · 6694e2ccbc71cc1e · report
negative_log_likelihood_mse IPL-UV/gaussflow/src/losses/nll.py community (archive-listed) unverified MIT (permissive) · 0d1d4f0a005a7547 · report
negative_log_likelihood_nats IPL-UV/gaussflow/src/losses/nll.py community (archive-listed) unverified MIT (permissive) · 0ce25394f9a9d587 · report
nll_2_bpd IPL-UV/rbig_jax/rbig_jax/losses.py community (archive-listed) unverified MIT (permissive) · 296a63ad389bce82 · report
nll_loss IPL-UV/rbig_jax/rbig_jax/stopping.py community (archive-listed) unverified MIT (permissive) · 36a600d9e04a706d · report
plot_2d_joint IPL-UV/gaussflow/src/viz/bivariate.py community (archive-listed) unverified MIT (permissive) · 674424cf743e0c7a · report
plot_2d_joint_probs IPL-UV/gaussflow/src/viz/bivariate.py community (archive-listed) unverified MIT (permissive) · 024690e22033fced · report
reverse_dataclass_params IPL-UV/rbig_jax/rbig_jax/utils.py community (archive-listed) unverified MIT (permissive) · 9c80db9b624b5c3a · report
safe_log IPL-UV/rbig_jax/rbig_jax/utils.py community (archive-listed) unverified MIT (permissive) · 105717a22f1e0c02 · report
train_model IPL-UV/rbig_jax/rbig_jax/training_old.py community (archive-listed) unverified MIT (permissive) · 20bd2735a605c5b4 · report
update_args_yaml IPL-UV/gaussflow/src/experiments/utils.py community (archive-listed) unverified MIT (permissive) · 02b9eaf38b243876 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionActivation NormalizationAffine CouplingBatch NormalizationGLOWInvertible 1x1 ConvolutionNormalizing FlowsRealNVP

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