Papers › Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm

Stein Variational Gradient Descent: A General Purpose Bayesian Inference Algorithm

16 Aug 2016NeurIPS 2016 12arXiv:1608.04471archive 2025-07-28

Qiang Liu, Dilin Wang

We propose a general purpose variational inference algorithm that forms a natural counterpart of gradient descent for optimization. Our method iteratively transports a set of particles to match the target distribution, by applying a form of functional gradient descent that minimizes the KL divergence. Empirical studies are performed on various real world models and datasets, on which our method is competitive with existing state-of-the-art methods. The derivation of our method is based on a new theoretical result that connects the derivative of KL divergence under smooth transforms with Stein's identity and a recently proposed kernelized Stein discrepancy, which is of independent interest.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (DartML/Stein-Variational-Gradient-Descent) was not harvested; the 5 samples below come from 2 community repositories.

Syntology 5 code samples harvested from 2 repositories linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 5 samples from 2 repositories, 5 ran (5 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

15 repositories listed; official and paper-mentioned ones first.

DartML/Stein-Variational-Gradient-Descent officialmentioned in papermentioned on GitHubtfMITSyntology: not harvested report
LMikeH/ocbnn-lmikh mentioned on GitHubpytorchMITSyntology: not harvested report
aleatory-science/smi_experiments mentioned on GitHubjaxSyntology: not harvested report
alegresor/vitruncate mentioned on GitHubNOASSERTIONSyntology: not harvested report
chenxy99/stein-variational-gradient-descent mentioned on GitHubpytorchSyntology: not harvested report
dilinwang820/Stein-Variational-Gradient-Descent mentioned on GitHubtfMITSyntology: not harvested report
feynmanliang/dist-svgd mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
larslorch/dibs mentioned on GitHubjaxSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DiBS: Differentiable Bayesian Structure Learning (arXiv:2105.11839; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
louissharrock/coin-svgd mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Coin Sampling: Gradient-Based Bayesian Inference without Learning Rates (arXiv:2301.11294; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
lpodl/Stein-Variational-Gradient-Descend mentioned on GitHubMITSyntology: not harvested report
lucadellalib/bayestorch mentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
lucadellalib/bdl-rul-svgd mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
MindSpore-scientific-2/code-11 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to LLMs as Zero-shot Graph Learners: Alignment of GNN Representations with LLM Token Embeddings (arXiv:2408.14512; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
activatedgeek/stein-gradient pytorchSyntology: not harvested report
pyro-ppl/pyro pytorchSyntology: not harvested 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

5 samples harvested: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran

Licence: 0 of the 5 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

feynmanliang/dist-svgd community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
kernel in 22 papers experiments/gmm.py ran fingerprinted MIT (permissive) · 552376bd52d01b1e · report fixture: signature x:Tensor/1/float, y:Tensor/1/float · returned Tensor · level recorded 2026-09-26
logp experiments/gmm.py ran fingerprinted MIT (permissive) · a88cde5db9694a61 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-26
lucadellalib/bayestorch community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
get_loc_scale bayestorch/distributions/utils.py ran Apache-2.0 (permissive) · d8d1608b34db5f1e · report fixture: signature distribution_cls:callable/0/?, parameters:list/1/Tensor, loc:float/0/float, scale:float/0/float, device:str/0/str, requires_grad:bool/0/bool, prefix:str/0/str · returned tuple · level recorded 2026-09-26
get_mixture_loc_scale bayestorch/distributions/utils.py ran Apache-2.0 (permissive) · 70758901a2163d8e · report fixture: signature distribution_cls:callable/0/?, parameters:generator/0/?, weights:tuple/1/float, locs:tuple/1/float, scales:tuple/1/float, device:str/0/str, requires_grad:bool/0/bool, prefix:str/0/str · returned tuple · level recorded 2026-09-26
nested_apply bayestorch/nn/utils.py ran Apache-2.0 (permissive) · 183a6a21b7a803b6 · report fixture: signature operator:callable/0/?, inputs:list/1/dict, dim:int/0/int · returned dict · level recorded 2026-09-26

Tasks

Bayesian InferenceVariational Inference

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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