Papers › Particle Semi-Implicit Variational Inference

Particle Semi-Implicit Variational Inference

30 Jun 2024arXiv:2407.00649archive 2025-07-28

Jen Ning Lim, Adam M. Johansen

Semi-implicit variational inference (SIVI) enriches the expressiveness of variational families by utilizing a kernel and a mixing distribution to hierarchically define the variational distribution. Existing SIVI methods parameterize the mixing distribution using implicit distributions, leading to intractable variational densities. As a result, directly maximizing the evidence lower bound (ELBO) is not possible, so they resort to one of the following: optimizing bounds on the ELBO, employing costly inner-loop Markov chain Monte Carlo runs, or solving minimax objectives. In this paper, we propose a novel method for SIVI called Particle Variational Inference (PVI) which employs empirical measures to approximate the optimal mixing distributions characterized as the minimizer of a free energy functional. PVI arises naturally as a particle approximation of a Euclidean--Wasserstein gradient flow and, unlike prior works, it directly optimizes the ELBO whilst making no parametric assumption about the mixing distribution. Our empirical results demonstrate that PVI performs favourably compared to other SIVI methods across various tasks. Moreover, we provide a theoretical analysis of the behaviour of the gradient flow of a related free energy functional: establishing the existence and uniqueness of solutions as well as propagation of chaos results.

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="2407.00649")

Code

Syntology Ran 4 of 11 code samples harvested from 2 repositories linked to this paper; 7 have no recorded run. Of those that ran: 1 ran · fixture could not drive it; 3 ran with no contract checked.

By repository: official repository: 11 samples from 2 repositories, 4 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jenninglim/pvi officialmentioned in papermentioned on GitHubjax report
longinyu/sivism officialmentioned in paperpytorch 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; 4 ran; 0 honoured the contract we drafted; 7 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
3ran
7unverified

Licence: 3 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 2 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.

PID jenninglim/pvi/src/trainers/pvi.py official repository ran · metamorphic tier: deterministic MIT (permissive) · 2bbf1397f3429464 · report
PIDOpt jenninglim/pvi/src/trainers/pvi.py official repository ran MIT (permissive) · 5ee9582619fa14ed · report
PIDParameters jenninglim/pvi/src/trainers/pvi.py official repository ran · metamorphic tier: well formed MIT (permissive) · d3956a1572644a78 · report
density_estimation longinYu/SIVISM/utils/density_estimation.py official repository ran · fixture could not drive it fingerprinted no licence file found · pointer only · 1f9e355031d1ccd1 · report
ID jenninglim/pvi/src/trainers/pvi.py official repository unverified MIT (permissive) · 7451ba00a6821b26 · report
PIDCarry jenninglim/pvi/src/trainers/pvi.py official repository unverified MIT (permissive) · 26762bfc7db6f0e4 · report
SGLD_lr longinYu/SIVISM/sgld_lr.py official repository unverified no licence file found · pointer only · dd340ac35b3291e4 · report
SGLD_toy longinYu/SIVISM/sgld_toyexample.py official repository unverified no licence file found · pointer only · 0e8133c37fe32af2 · report
Target jenninglim/pvi/src/trainers/pvi.py official repository unverified MIT (permissive) · 03bec2405a6becc0 · report
de_particle_grad jenninglim/pvi/src/trainers/pvi.py official repository unverified MIT (permissive) · 8c022fb203bde4f5 · report
de_particle_step jenninglim/pvi/src/trainers/pvi.py official repository unverified MIT (permissive) · a30f6968ced8a8c9 · report

Tasks

Variational Inference

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Variational Inference

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