Papers › Algorithms for mean-field variational inference via polyhedral optimization in the...

Algorithms for mean-field variational inference via polyhedral optimization in the Wasserstein space

5 Dec 2023arXiv:2312.02849archive 2025-07-28

Yiheng Jiang, Sinho Chewi, Aram-Alexandre Pooladian

We develop a theory of finite-dimensional polyhedral subsets over the Wasserstein space and optimization of functionals over them via first-order methods. Our main application is to the problem of mean-field variational inference, which seeks to approximate a distribution π over ℝᵈ by a product measure π^⋆. When π is strongly log-concave and log-smooth, we provide (1) approximation rates certifying that π^⋆ is close to the minimizer π^⋆_♢ of the KL divergence over a polyhedral set 𝒫_♢, and (2) an algorithm for minimizing KL(·‖π) over 𝒫_♢ based on accelerated gradient descent over ℝᵈ. As a byproduct of our analysis, we obtain the first end-to-end analysis for gradient-based algorithms for MFVI.

PaperPDFCodeCode 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

Syntology 11 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 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: official repository: 11 samples from 1 repository, 11 ran (11 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.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

apooladian/mfvi officialmentioned in papermentioned on GitHubMITSyntology: 11 samples, 11 ran (0 instrument-failed) · 0 unverified 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

11 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 0 violated, 10 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 last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
10ran

Licence: 0 of the 11 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 apooladian/mfvi. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

apooladian/mfvi official repository 11 samples, 11 ran (0 instrument-failed) · 0 unverified
V_Gaussian_highd gaussian_utils.py ran MIT (permissive) · 987b4f5873f65d5b · report fixture: signature x:ndarray/2/float, mean:ndarray/2/float, invcov:ndarray/2/float · returned ndarray · level recorded 2026-09-24
V_logistic BayesianUtils.py ran MIT (permissive) · b74a555b9f9adb40 · report fixture: signature theta:ndarray/1/float, Y:ndarray/1/float, X:ndarray/1/float · returned ndarray · level recorded 2026-09-24
build_M_FAST misc_utils.py ran MIT (permissive) · 5a44c60d315c346b · report fixture: signature dim:int/0/int, mesh:float/0/float, truncation:int/0/int · returned tuple · level recorded 2026-09-24
compute_entropy_gradient_highd optimization_utils.py ran MIT (permissive) · 0f34e9af21c91c24 · report fixture: signature alpha:Tensor/0/float, lamb:Tensor/0/float, mesh:Tensor/2/float, gradent_numerator:Tensor/2/float · returned Tensor · level recorded 2026-09-24
gaussian_int misc_utils.py ran fingerprinted MIT (permissive) · 8139bf2df4a8f4ec · report fixture: signature a:float/0/float, b:float/0/float · returned float64 · level recorded 2026-09-24
gaussian_x_int misc_utils.py ran fingerprinted MIT (permissive) · c4a97d909afb2eea · report fixture: signature a:float/0/float, b:float/0/float · returned float64 · level recorded 2026-09-24
gradV_Gaussian_highd gaussian_utils.py ran MIT (permissive) · 781f488f0dbe4f77 · report fixture: signature x:ndarray/2/float, mean:ndarray/1/float, invcov:ndarray/2/float · returned ndarray · level recorded 2026-09-24
gradV_logistic BayesianUtils.py ran MIT (permissive) · 3c9084399513a9fe · report fixture: signature theta:ndarray/1/float, Y:ndarray/1/float, X:ndarray/2/float · returned ndarray · level recorded 2026-09-24
langevin_monte_carlo lmc_algorithm.py ran MIT (permissive) · af0e778af250e84c · report fixture: signature gradV:callable/0/?, N_samples:int/0/int, dim:int/0/int, h:float/0/float, iters:int/0/int, tol:float/0/float · returned ndarray · level recorded 2026-09-24
rho_gaussian_samples gaussian_utils.py ran fingerprinted MIT (permissive) · 2c7490d7cda8093a · report fixture: signature num_samples:int/0/int, dim:int/0/int · returned ndarray · level recorded 2026-09-24
softmax in 240 papers
census: 53 implementations from 63 papers, 16 distinct outputs across 8 buckets, one shared input per bucket
BayesianUtils.py ran · honoured contract fingerprinted MIT (permissive) · 5ac707ebfd83b4ce · report fixture: signature x:ndarray/2/float · returned ndarray · level recorded 2026-09-24

Tasks

Variational Inference

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SET

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