SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2401.11665 · 2024

Accelerating Approximate Thompson Sampling with Underdamped Langevin Monte Carlo

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; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures 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/2401.11665.json · badge: /api/ran/2401.11665.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
haoyangzheng1996/ts_ulmc canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
FunctionStatusWhere it lives
over_damped Ran
ran; our contract draft was wrong, not the code
haoyangzheng1996/ts_ulmc/model/langevin.py
code served (permissive licence) · get_code("03f65e7584c00c79")
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 ndarray, ndim 1, dtype family float, shape (4,) 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 numpy as np
import random

np.random.seed(0)
random.seed(0)

# Create observations: list of arrays representing data points
# Each observation should be a 1D array of dimension 4
observations = [
    np.random.randn(4),
    np.random.randn(4),
    np.random.randn(4),
    np.random.randn(4),
    np.random.randn(4),
    np.random.randn(4),
    np.random.randn(4),
    np.random.randn(4),
    np.random.randn(4),
    np.random.randn(4),
    np.random.randn(4),
    np.random.randn(4),
]

# step_size: learning rate for the gradient descent update
step_size = 0.01

# n_iterations: number of iterations to run
n_iterations = 5

# prior_mean: prior mean for the Bayesian model
prior_mean = np.zeros(4)

# prior_variance_inv: inverse of prior variance (precision matrix)
prior_variance_inv = np.eye(4)

# current: current estimate (starting point)
current = np.random.randn(4)

# n_round: number of rounds
n_round = 1

# batch_size: size of mini-batch
batch_size = 10

# prior_type: type of prior (None means use full prior)
prior_type = None

ARGS = {
    "observations": observations,
    "step_size": step_size,
    "n_iterations": n_iterations,
    "prior_mean": prior_mean,
    "prior_variance_inv": prior_variance_inv,
    "current": current,
    "n_round": n_round,
    "batch_size": batch_size,
    "prior_type": prior_type,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 1, dtype family float, shape (4,) — shape (4,) 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: none by the harness; any seed is in the setup block
under_damped Ran
ran; our contract draft was wrong, not the code
haoyangzheng1996/ts_ulmc/model/langevin.py
code served (permissive licence) · get_code("9043918a85931f5b")
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 2, 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 numpy as np
import random

random.seed(0)
np.random.seed(0)

# Construct arguments for under_damped function

# observations: list of numpy arrays (batches of observations)
dim = 4
observations = [np.random.randn(dim) for _ in range(15)]

# step_size: float
step_size = 0.01

# n_iterations: int
n_iterations = 3

# prior_mean: numpy array of shape (dim,)
prior_mean = np.zeros(dim)

# prior_variance_inv: numpy array (inverse covariance matrix, shape (dim, dim))
prior_variance_inv = np.eye(dim)

# current: tuple of (x_mean, v_mean), each shape (dim,)
current = (np.random.randn(dim), np.random.randn(dim))

# n_round: int
n_round = 1

# gamma: float (damping parameter)
gamma = 2.0

# L: float (smoothness parameter)
L = 1.0

# batch_size: int
batch_size = 10

# prior_type: None or string
prior_type = None

ARGS = {
    'observations': observations,
    'step_size': step_size,
    'n_iterations': n_iterations,
    'prior_mean': prior_mean,
    'prior_variance_inv': prior_variance_inv,
    'current': current,
    'n_round': n_round,
    'gamma': gamma,
    'L': L,
    'batch_size': batch_size,
    'prior_type': prior_type,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 2, 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

Approximate Thompson sampling with Langevin Monte Carlo broadens its reach from Gaussian posterior sampling to encompass more general smooth posteriors. However, it still encounters scalability issues in high-dimensional problems when demanding high accuracy. To address this, we propose an approximate Thompson sampling strategy, utilizing underdamped Langevin Monte Carlo, where the latter is the go-to workhorse for simulations of high-dimensional posteriors. Based on the standard smoothness and log-concavity conditions, we study the accelerated posterior concentration and sampling using a specific potential function. This design improves the sample complexity for realizing logarithmic regrets from $\mathcal{\tilde O}(d)$ to $\mathcal{\tilde O}(\sqrt{d})$. The scalability and robustness of our algorithm are also empirically validated through synthetic experiments in high-dimensional bandit problems.

For agents

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

get_harvested_code_for_paper("2401.11665")
get_code_for_paper("2401.11665")
have("2401.11665")

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

curl https://syntology.ai/api/ran/2401.11665.json

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

[![Syntology run record](https://syntology.ai/api/ran/2401.11665.svg)](https://syntology.ai/paper/2401.11665)

Connect an agent — have() is free.