SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.00323 · 2020

Convergence of Sparse Variational Inference in Gaussian Processes Regression

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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 0 have no contract verdict; 1 failure of our instrument; 0 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/2008.00323.json · badge: /api/ran/2008.00323.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
markvdw/RobustGP canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
FunctionStatusWhere it lives
accept_or_reject Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
markvdw/RobustGP/robustgp/init_methods/kdpp_mcmc.py
code served (permissive licence) · get_code("c47bc6a4bc0512ca")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple. The image it ran in was not recorded. If your copy returns the same type 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 numpy as np
import scipy.linalg

class MockKernel:
    """Mock kernel wrapper that computes kernel matrices"""
    def __call__(self, X1, X2, full_cov=False):
        # Simple RBF-like kernel: exp(-||x1-x2||^2)
        if X2 is None:
            # Diagonal case when full_cov=True
            result = np.ones((X1.shape[0], 1))
            return result
        else:
            # Compute pairwise distances
            dists = np.sum((X1[:, None, :] - X2[None, :, :]) ** 2, axis=2)
            kernel_matrix = np.exp(-dists)
            return kernel_matrix

# Create small training data
X = np.random.randn(5, 4).astype(np.float64)

# Create a kernel instance
kernel = MockKernel()

# Create a small active set indices (Z = X[indices])
indices = np.array([0, 1, 2], dtype=int)
Z = X[indices]

# Compute initial QR decomposition of kernel matrix K_uu where u = Z
K_uu = kernel(Z, Z)
Q, R = scipy.linalg.qr(K_uu)

# Parameters for the swap
s = 1  # index within the active set to potentially remove
t = 3  # index in X to potentially add

ARGS = {
    'X': X,
    'kernel': kernel,
    'indices': indices,
    's': s,
    't': t,
    'Q': Q,
    'R': R,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
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: none by the harness; any seed is in the setup block
compute_model_stats Ran
ran, honoured the contract we drafted
markvdw/RobustGP/robustgp_experiments/init_z/jug_init_inducing_opt.py
code served (permissive licence) · get_code("3b16f2ced041aeac")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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
import numpy as np
from unittest.mock import Mock

torch.manual_seed(0)

class SimpleGPModel:
    """Minimal stand-in for a GP model with required methods."""
    
    def __init__(self):
        self.X_train = torch.randn(2, 4)
        self.Y_train = torch.randn(2, 3)
    
    def robust_maximum_log_likelihood_objective(self, restore_jitter=False):
        """Returns a tensor wrapped in a numpy-convertible object."""
        result = Mock()
        result.numpy = lambda: np.array(1.5)
        return result
    
    def upper_bound(self):
        """Returns a tensor wrapped in a numpy-convertible object."""
        result = Mock()
        result.numpy = lambda: np.array(2.0)
        return result
    
    def predict_f(self, X):
        """Returns predictions as [mean, variance] tuple."""
        mean = torch.randn(X.shape[0], 3)
        variance = torch.ones(X.shape[0], 3) * 0.1
        mean_mock = Mock()
        mean_mock.numpy = lambda: mean.numpy()
        return (mean_mock, variance)
    
    def predict_log_density(self, data):
        """Returns log density predictions."""
        X, Y = data
        batch_size = X.shape[0]
        log_density = np.random.randn(batch_size)
        return log_density


class Experiment:
    """Minimal stand-in for experiment object."""
    
    def __init__(self):
        self.model = SimpleGPModel()
        self.X_test = torch.randn(2, 4)
        self.Y_test = np.random.randn(2, 3)


ARGS = {
    "exp": Experiment()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

Gaussian processes are distributions over functions that are versatile and mathematically convenient priors in Bayesian modelling. However, their use is often impeded for data with large numbers of observations, $N$, due to the cubic (in $N$) cost of matrix operations used in exact inference. Many solutions have been proposed that rely on $M \ll N$ inducing variables to form an approximation at a cost of $\mathcal{O}(NM^2)$. While the computational cost appears linear in $N$, the true complexity depends on how $M$ must scale with $N$ to ensure a certain quality of the approximation. In this work, we investigate upper and lower bounds on how $M$ needs to grow with $N$ to ensure high quality approximations. We show that we can make the KL-divergence between the approximate model and the exact posterior arbitrarily small for a Gaussian-noise regression model with $M\ll N$. Specifically, for the popular squared exponential kernel and $D$-dimensional Gaussian distributed covariates, $M=\mathcal{O}((\log N)^D)$ suffice and a method with an overall computational cost of $\mathcal{O}(N(\log N)^{2D}(\log\log N)^2)$ can be used to perform inference.

For agents

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

get_harvested_code_for_paper("2008.00323")
get_code_for_paper("2008.00323")
have("2008.00323")

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

curl https://syntology.ai/api/ran/2008.00323.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.00323.svg)](https://syntology.ai/paper/2008.00323)

Connect an agent — have() is free.