SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2210.06447 · NeurIPS · 2022

Sampling in Constrained Domains with Orthogonal-Space Variational Gradient Descent

Qiang Liu, Ruqi Zhang, Xin Tong

arXiv · PDF · Open in the Atlas

Code that ran

3 of 4 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; 1 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 1 no recorded run), measured 2026-11-22; 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/2210.06447.json · badge: /api/ran/2210.06447.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
ruqizhang/o-gradient canonical (classifier label)
classifier basis: classifier_2025
3 ran · 1 no recorded run
FunctionStatusWhere it lives
O_Langevin Ran
ran on a synthesized input
ruqizhang/o-gradient/samplers.py
pointer only (licence: NONE) · get_code("73f9844f4eb042cc")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ruqizhang/o-gradient when it was checked. 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.

compute_w2 Ran
ran, honoured the contract we drafted
ruqizhang/o-gradient/main_synthetic.py
pointer only (licence: NONE) · get_code("3b15204af8874b1a")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ruqizhang/o-gradient when it was checked. 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.

plot_2d_zero Ran
ran; our contract draft was wrong, not the code
ruqizhang/o-gradient/main_synthetic.py
pointer only (licence: NONE) · get_code("19a0a20172bf427d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ruqizhang/o-gradient when it was checked. 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.

adjust_learning_rate Not yet run
unverified (harvested, no recorded run)
ruqizhang/o-gradient/main_bnn_langevin.py
pointer only (licence: NONE) · get_code("31a4a526653a1689")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, ruqizhang/o-gradient when it was checked. 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 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 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 4 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

Sampling methods, as important inference and learning techniques, are typically designed for unconstrained domains. However, constraints are ubiquitous in machine learning problems, such as those on safety, fairness, robustness, and many other properties that must be satisfied to apply sampling results in real-life applications. Enforcing these constraints often leads to implicitly-defined manifolds, making efficient sampling with constraints very challenging. In this paper, we propose a new variational framework with a designed orthogonal-space gradient flow (O-Gradient) for sampling on a manifold G 0 defined by general equality constraints. O-Gradient decomposes the gradient into two parts: one decreases the distance to G 0 and the other decreases the KL divergence in the orthogonal space. While most existing manifold sampling methods require initialization on G 0 , O-Gradient does not require such prior knowledge. We prove that O-Gradient converges to the target constrained distribution with rate O(1/the number of iterations) under mild conditions. Our proof relies on a new Stein characterization of conditional measure which could be of independent interest. We implement O-Gradient through both Langevin dynamics and Stein variational gradient descent and demonstrate its effectiveness in various experiments, including Bayesian deep neural networks.

For agents

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

get_harvested_code_for_paper("2210.06447")
get_code_for_paper("2210.06447")
have("2210.06447")

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

curl https://syntology.ai/api/ran/2210.06447.json

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

[![Syntology run record](https://syntology.ai/api/ran/2210.06447.svg)](https://syntology.ai/paper/2210.06447)

Connect an agent — have() is free.