Papers › Block Neural Autoregressive Flow

Block Neural Autoregressive Flow

9 Apr 2019arXiv:1904.04676archive 2025-07-28

Nicola De Cao, Ivan Titov, Wilker Aziz

Normalising flows (NFS) map two density functions via a differentiable bijection whose Jacobian determinant can be computed efficiently. Recently, as an alternative to hand-crafted bijections, Huang et al. (2018) proposed neural autoregressive flow (NAF) which is a universal approximator for density functions. Their flow is a neural network (NN) whose parameters are predicted by another NN. The latter grows quadratically with the size of the former and thus an efficient technique for parametrization is needed. We propose block neural autoregressive flow (B-NAF), a much more compact universal approximator of density functions, where we model a bijection directly using a single feed-forward network. Invertibility is ensured by carefully designing each affine transformation with block matrices that make the flow autoregressive and (strictly) monotone. We compare B-NAF to NAF and other established flows on density estimation and approximate inference for latent variable models. Our proposed flow is competitive across datasets while using orders of magnitude fewer parameters.

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="1904.04676")

Code

Syntology Ran 2 of 4 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 2 ran · our draft was wrong.

By repository: official repository: 4 samples from 1 repository, 2 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

nicola-decao/BNAF officialmentioned in papermentioned on GitHubpytorch report
metachenyiyan/BreezeForest mentioned on GitHubpytorch report
sshish/NF 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

4 samples harvested; 2 ran; 0 honoured the contract we drafted; 2 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.

2ran · our draft was wrong
2unverified

Licence: 0 of the 4 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 nicola-decao/BNAF. “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.

compute_log_p_x nicola-decao/BNAF/toy2d.py official repository ran · our draft was wrong MIT (permissive) · 1e3e1419bbf70774 · report
save_model nicola-decao/BNAF/density_estimation.py official repository ran · our draft was wrong MIT (permissive) · c7c2cd135ec55792 · report
create_model nicola-decao/BNAF/toy2d.py official repository unverified MIT (permissive) · f2977965fe47a3fe · report
create_model nicola-decao/BNAF/density_estimation.py official repository unverified MIT (permissive) · 87c781818f839148 · report

Tasks

Density EstimationNormalising Flows

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Density Estimation BSDS300 B-NAF Log-likelihood 157.36 #3 of 5 Archive leaderboard report
Density Estimation Caltech-101 B-NAF NLL 105.42 #1 of 3 Archive leaderboard report
Density Estimation Caltech-101 B-NAF Negative ELBO 94.91 #1 of 3 Archive leaderboard report
Density Estimation Freyfaces B-NAF NLL 4.42 #1 of 3 Archive leaderboard report
Density Estimation Freyfaces B-NAF Negative ELBO 4.33 #1 of 3 Archive leaderboard report
Density Estimation OMNIGLOT B-NAF NLL 100.08 #1 of 4 Archive leaderboard report
Density Estimation OMNIGLOT B-NAF Negative ELBO 94.83 #1 of 4 Archive leaderboard report
Density Estimation UCI GAS B-NAF Log-likelihood 12.06 #1 of 5 Archive leaderboard report
Density Estimation UCI HEPMASS B-NAF Log-likelihood -14.71 #3 of 5 Archive leaderboard report
Density Estimation UCI MINIBOONE B-NAF Log-likelihood -8.95 #4 of 5 Archive leaderboard report
Density Estimation UCI POWER B-NAF Log-likelihood 0.61 #3 of 6 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