SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.07134 · 2020

Tight Differential Privacy for Discrete-Valued Mechanisms and for the Subsampled Gaussian Mechanism Using FFT

arXiv · PDF · Open in the Atlas

Code that ran

3 of 7 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 3 have no contract verdict; 0 failures of our instrument; 4 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/2006.07134.json · badge: /api/ran/2006.07134.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
DPBayes/PLD-Accountant canonical (classifier label)
classifier basis: census
3 ran · 4 no recorded run
FunctionStatusWhere it lives
df Ran
ran on a synthesized input
DPBayes/PLD-Accountant/fourier_accountant/experimental/subsampled_gaussian_bounds.py
code served (permissive licence) · get_code("d90ae7ca45fead6d")
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 (5,) 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

# Set random seed for reproducibility
np.random.seed(0)

# Create valid arguments for the df function
x = np.array([0.1, 0.5, 1.0, 1.5, 2.0])  # Discretized evaluation points
sigma = 0.5  # Gaussian mechanism noise level (positive scalar)
q = 0.01  # Subsampling ratio (between 0 and 1)

ARGS = {
    "x": x,
    "sigma": sigma,
    "q": q
}
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 (5,) — shape (5,) 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
f Ran
ran on a synthesized input
DPBayes/PLD-Accountant/fourier_accountant/experimental/subsampled_gaussian_bounds.py
code served (permissive licence) · get_code("2df6e3aed39035e5")
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

# Construct arguments for f(x, sigma, q)
# x: Discretized evaluation points (numpy array)
# sigma: Gaussian mechanism noise level (float)
# q: Subsampling ratio (float)

x = np.array([0.1, 0.5, 1.0, 2.0])
sigma = 0.5
q = 0.01

ARGS = {
    "x": x,
    "sigma": sigma,
    "q": q
}
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
get_L Ran
ran on a synthesized input
DPBayes/PLD-Accountant/fourier_accountant/experimental/adaptive_discrete_DP.py
code served (permissive licence) · get_code("31fb5847e2b7de82")
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 numpy as np

# Analyze the function to understand what P1 and P2 need to be:
# - They are indexed with P1[i] and P2[i], so they need to be indexable
# - They need to support division (P1[i] / P2[i])
# - They need to support exponentiation with **
# - They are used in loops: for i in range(0, len(P1))
# - So they need len() to work
# These are probability distributions, so they should be numpy arrays of positive floats

# Create valid probability distributions P1 and P2
P1 = np.array([0.2, 0.3, 0.25, 0.25], dtype=np.float64)
P2 = np.array([0.25, 0.25, 0.25, 0.25], dtype=np.float64)

# Ensure they are valid probability distributions (sum to 1)
P1 = P1 / np.sum(P1)
P2 = P2 / np.sum(P2)

ARGS = {
    'P1': P1,
    'P2': P2,
    'target_eps': 1.0,
    'ncomp': 500,
    'error_tol': 1e-05
}
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 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
get_delta_lower Not yet run
unverified (harvested, no recorded run)
DPBayes/PLD-Accountant/fourier_accountant/experimental/adaptive_discrete_DP.py
code served (permissive licence) · get_code("fec641c792292cb5")
How it ran

no invocation recorded.

get_delta_max Not yet run
unverified (harvested, no recorded run)
DPBayes/PLD-Accountant/fourier_accountant/experimental/subsampled_gaussian_bounds.py
code served (permissive licence) · get_code("afc443cccf602f46")
How it ran

no invocation recorded.

get_delta_upper Not yet run
unverified (harvested, no recorded run)
DPBayes/PLD-Accountant/fourier_accountant/experimental/adaptive_discrete_DP.py
code served (permissive licence) · get_code("f82b5046949ce03c")
How it ran

no invocation recorded.

get_epsilon Not yet run
unverified (harvested, no recorded run)
DPBayes/PLD-Accountant/fourier_accountant/experimental/binomial_mechanism.py
code served (permissive licence) · get_code("ff04203c9035f8c5")
How it ran

no invocation recorded.

Also present in other papers' code

Of 7 samples lifted from this paper's linked repositories, 7 carry a function identity and 0 do not. Of the 7 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 7 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

We propose a numerical accountant for evaluating the tight $(\varepsilon,δ)$-privacy loss for algorithms with discrete one dimensional output. The method is based on the privacy loss distribution formalism and it uses the recently introduced fast Fourier transform based accounting technique. We carry out an error analysis of the method in terms of moment bounds of the privacy loss distribution which leads to rigorous lower and upper bounds for the true $(\varepsilon,δ)$-values. As an application, we present a novel approach to accurate privacy accounting of the subsampled Gaussian mechanism. This completes the previously proposed analysis by giving strict lower and upper bounds for the privacy parameters. We demonstrate the performance of the accountant on the binomial mechanism and show that our approach allows decreasing noise variance up to 75 percent at equal privacy compared to existing bounds in the literature. We also illustrate how to compute tight bounds for the exponential mechanism applied to counting queries.

For agents

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

get_harvested_code_for_paper("2006.07134")
get_code_for_paper("2006.07134")
have("2006.07134")

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

curl https://syntology.ai/api/ran/2006.07134.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.07134.svg)](https://syntology.ai/paper/2006.07134)

Connect an agent — have() is free.