SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.16408 · 2024

Stable Training of Normalizing Flows for High-dimensional Variational Inference

arXiv · PDF · Open in the Atlas

Code that ran

11 of 15 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 4 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 6 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2402.16408.json · badge: /api/ran/2402.16408.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
andrade-stats/normalizing-flows canonical (classifier label)
classifier basis: census
11 ran · 4 no recorded run
FunctionStatusWhere it lives
chi2_simple Ran
ran, honoured the contract we drafted
andrade-stats/normalizing-flows/core_adjusted.py
pointer only (licence: NOASSERTION) · get_code("4afcfcc45bcc2493")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, andrade-stats/normalizing-flows (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

getAllModuleIndices Ran
ran, honoured the contract we drafted
andrade-stats/normalizing-flows/analysis.py
pointer only (licence: NOASSERTION) · get_code("822c2d0cbf925d06")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, andrade-stats/normalizing-flows (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

getEmptyStatDic Ran
ran; our contract draft was wrong, not the code
andrade-stats/normalizing-flows/analysis.py
pointer only (licence: NOASSERTION) · get_code("510987f49c20c772")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, andrade-stats/normalizing-flows (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

getNrFalseDetections Ran
ran, violated the contract we drafted
andrade-stats/normalizing-flows/evaluation.py
pointer only (licence: NOASSERTION) · get_code("399570b135a60e80")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, andrade-stats/normalizing-flows (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

getOutlierRecall Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
andrade-stats/normalizing-flows/evaluation.py
pointer only (licence: NOASSERTION) · get_code("f8b7c4915f5875d0")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, andrade-stats/normalizing-flows (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

getVec Ran
ran, honoured the contract we drafted
andrade-stats/normalizing-flows/analysis.py
pointer only (licence: NOASSERTION) · get_code("8b2d5fe633436d0a")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, andrade-stats/normalizing-flows (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_log_prob_multivariate_t Ran
ran; our contract draft was wrong, not the code
andrade-stats/normalizing-flows/densities.py
pointer only (licence: NOASSERTION) · get_code("94e580bb6e619979")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, andrade-stats/normalizing-flows (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

leakyClamp Ran
ran; our contract draft was wrong, not the code
andrade-stats/normalizing-flows/new_flows.py
pointer only (licence: NOASSERTION) · get_code("40fd67c68c2dce9b")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, andrade-stats/normalizing-flows (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

showOutlierDetectionPerformance_power_fdr Ran
ran, honoured the contract we drafted
andrade-stats/normalizing-flows/evaluation.py
pointer only (licence: NOASSERTION) · get_code("cbd75af666284269")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, andrade-stats/normalizing-flows (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

softClampAsymAdvanced Ran
ran; our contract draft was wrong, not the code
andrade-stats/normalizing-flows/new_flows.py
pointer only (licence: NOASSERTION) · get_code("add8722ad720659f")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, andrade-stats/normalizing-flows (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

softClampAsymNew Ran
ran; our contract draft was wrong, not the code
andrade-stats/normalizing-flows/new_flows.py
pointer only (licence: NOASSERTION) · get_code("c039b5cd7098af7d")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, andrade-stats/normalizing-flows (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_log_prob_inv_gamma Not yet run
unverified (harvested, no recorded run)
andrade-stats/normalizing-flows/densities.py
pointer only (licence: NOASSERTION) · get_code("70e480ffce9632e5")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, andrade-stats/normalizing-flows (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

loadArray Not yet run
unverified (harvested, no recorded run)
andrade-stats/normalizing-flows/commons.py
pointer only (licence: NOASSERTION) · get_code("8487032f2eeabb41")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, andrade-stats/normalizing-flows (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

loadStatistics Not yet run
unverified (harvested, no recorded run)
andrade-stats/normalizing-flows/commons.py
pointer only (licence: NOASSERTION) · get_code("8c4b93348da52ad9")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, andrade-stats/normalizing-flows (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

moveToDevice Not yet run
unverified (harvested, no recorded run)
andrade-stats/normalizing-flows/commons.py
pointer only (licence: NOASSERTION) · get_code("50ad8e41c0b7de01")
How it ran

The body of this sample is withheld: GitHub could not classify the licence of this paper's repository, andrade-stats/normalizing-flows (NOASSERTION). The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 15 samples lifted from this paper's linked repositories, 15 carry a function identity and 0 do not. Of the 15 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 15 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Variational inference with normalizing flows (NFs) is an increasingly popular alternative to MCMC methods. In particular, NFs based on coupling layers (Real NVPs) are frequently used due to their good empirical performance. In theory, increasing the depth of normalizing flows should lead to more accurate posterior approximations. However, in practice, training deep normalizing flows for approximating high-dimensional posterior distributions is often infeasible due to the high variance of the stochastic gradients. In this work, we show that previous methods for stabilizing the variance of stochastic gradient descent can be insufficient to achieve stable training of Real NVPs. As the source of the problem, we identify that, during training, samples often exhibit unusual high values. As a remedy, we propose a combination of two methods: (1) soft-thresholding of the scale in Real NVPs, and (2) a bijective soft log transformation of the samples. We evaluate these and other previously proposed modification on several challenging target distributions, including a high-dimensional horseshoe logistic regression model. Our experiments show that with our modifications, stable training of Real NVPs for posteriors with several thousand dimensions is possible, allowing for more accurate marginal likelihood estimation via importance sampling. Moreover, we evaluate several common training techniques and architecture choices and provide practical advise for training NFs for high-dimensional variational inference.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.16408")
get_code_for_paper("2402.16408")
have("2402.16408")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2402.16408.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2402.16408.svg)](https://syntology.ai/paper/2402.16408)

Connect an agent — have() is free.