SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.19147 · NeurIPS · 2023

Conditional score-based diffusion models for Bayesian inference in infinite dimensions

Josselin Garnier, Ali Siahkoohi, Maarten De Hoop, Lorenzo Baldassari, Knut Sølna

arXiv · PDF · Open in the Atlas

Code that ran

1 of 3 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 0 failures of our instrument; 2 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/2305.19147.json · badge: /api/ran/2305.19147.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
alisiahkoohi/csgm canonical (classifier label)
classifier basis: classifier_2025
1 ran · 2 no recorded run
FunctionStatusWhere it lives
FourierNeuralLayer1D Ran
ran on a synthesized input
alisiahkoohi/csgm/csgm/network_conditional.py
code served (permissive licence) · get_code("b4537186753cc754")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 3, dtype family float, shape (2, 4, 16) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

INIT_ARGS = {
    'in_channels': 3,
    'out_channels': 4,
    'modes': 2,
}

ARGS = {
    'x': torch.randn(2, 3, 16),
}

if __name__ == '__main__':
    from torch import nn
    
    class FourierNeuralLayer1D(nn.Module):
        """A Fourier neural layer object.

        A Fourier neural layer involves a Fourier transform over the spatial
        dimensions of the input, followed by a learned elementwise multiplication
        and an inverse Fourier transform.

        Attributes:
            in_channels: An integer indicating the number of input channels.
            out_channels: An integer indicating the number of output channels.
            modes: An integer indicating the number of Fourier modes to update.
            weights: A list containing two Tensors of size `(in_channels,
                out_channels, modes, modes)` as weights for the layer.
        """

        def __init__(self, in_channels: int, out_channels: int, modes: int):
            """Initializes a Fourier neural layer object.

            Args:
                in_channels: An integer indicating the number of input channels.
                out_channels: An integer indicating the number of output channels.
                modes: An integer indicating the number of Fourier modes to update.
            """
            super().__init__()
            self.in_channels = in_channels
            self.out_channels = out_channels
            self.modes = modes
            scale = 1.0 / (in_channels * out_channels)
            self.weights = nn.ParameterList([nn.Parameter(scale * torch.rand(in_channels, out_channels, self.modes, dtype=torch.cfloat)), nn.Parameter(scale * torch.rand(in_channels, out_channels, self.modes, dtype=torch.cfloat))])

        def forward(self, x: torch.Tensor) -> torch.Tensor:
            """Forward pass of the Fourier neural layer.

            Args:
                x: A torch.Tensor of size `(batch_size, in_channels, length)`.

            Returns:
                A torch.Tensor of size `(batch_size, out_channels, length)`,
                which is The outcome of the `FourierNeuralLayer1D`.
            """
            x_fft = torch.fft.rfft(x)
            out = torch.zeros([x.shape[0], self.out_channels, x.shape[-1] // 2 + 1], dtype=torch.cfloat, device=x.device)
            out[:, :, :self.modes] = torch.einsum('bix, iox -> box', x_fft[..., :self.modes], self.weights[0])
            out[:, :, -self.modes:] = torch.einsum('bix, iox -> box', x_fft[..., -self.modes:], self.weights[1])
            return torch.fft.irfft(out, n=x.shape[-1])

    layer = FourierNeuralLayer1D(**INIT_ARGS)
    output = layer(**ARGS)
    print(f"Input shape: {ARGS['x'].shape}")
    print(f"Output shape: {output.shape}")
    print(f"Output dtype: {output.dtype}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 4, 16) — shape (2, 4, 16) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
ConditionalScoreModel1D Not yet run
unverified (harvested, no recorded run)
alisiahkoohi/csgm/csgm/network_conditional.py
code served (permissive licence) · get_code("778cdb06a02005ac")
How it ran

no invocation recorded.

FourierNeuralOperator1D Not yet run
unverified (harvested, no recorded run)
alisiahkoohi/csgm/csgm/network_conditional.py
code served (permissive licence) · get_code("af8861c727b86643")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 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 3 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

Since their initial introduction, score-based diffusion models (SDMs) have been successfully applied to solve a variety of linear inverse problems in finite-dimensional vector spaces due to their ability to efficiently approximate the posterior distribution. However, using SDMs for inverse problems in infinite-dimensional function spaces has only been addressed recently, primarily through methods that learn the unconditional score. While this approach is advantageous for some inverse problems, it is mostly heuristic and involves numerous computationally costly forward operator evaluations during posterior sampling. To address these limitations, we propose a theoretically grounded method for sampling from the posterior of infinite-dimensional Bayesian linear inverse problems based on amortized conditional SDMs. In particular, we prove that one of the most successful approaches for estimating the conditional score in finite dimensions-the conditional denoising estimator-can also be applied in infinite dimensions. A significant part of our analysis is dedicated to demonstrating that extending infinite-dimensional SDMs to the conditional setting requires careful consideration, as the conditional score typically blows up for small times, contrarily to the unconditional score. We conclude by presenting stylized and large-scale numerical examples that validate our approach, offer additional insights, and demonstrate that our method enables large-scale, discretization-invariant Bayesian inference.

For agents

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

get_harvested_code_for_paper("2305.19147")
get_code_for_paper("2305.19147")
have("2305.19147")

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

curl https://syntology.ai/api/ran/2305.19147.json

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

[![Syntology run record](https://syntology.ai/api/ran/2305.19147.svg)](https://syntology.ai/paper/2305.19147)

Connect an agent — have() is free.