SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.12997 · NeurIPS · 2021

Bayesian Optimization with High-Dimensional Outputs

Andrew Wilson, Wesley Maddox, Maximilian Balandat, Eytan Bakshy

arXiv · PDF · Open in the Atlas

Code that ran

13 of 18 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, 1 violated it and 8 have no contract verdict; 3 failures of our instrument; 5 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/2106.12997.json · badge: /api/ran/2106.12997.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
msu-coinlab/pymoo canonical (classifier label)
classifier basis: census
8 ran · 2 no recorded run
wjmaddox/mtgp_sampler canonical (classifier label)
classifier basis: census
4 ran · 3 no recorded run
copy not recorded community
not in the paper's declared repositories
1 ran · 0 no recorded run
FunctionStatusWhere it lives
constr_to_cv Ran
ran on a synthesized input
msu-coinlab/pymoo/pymoo/core/individual.py
code served (permissive licence) · get_code("4dd1c3e56754b861")
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 float64, ndim 0, 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

ARGS = {
    "c": np.array([0.5, 1.2, 0.3, 2.1]),
    "eps": 0.1,
    "scale": 2.0,
    "pow": 0.5,
    "func": np.mean
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
default_attr Ran
ran on a synthesized input
msu-coinlab/pymoo/pymoo/core/duplicate.py
code served (permissive licence) · get_code("aaf5cc78c99f164e")
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 Tensor, ndim 2, dtype family float, shape (2, 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 torch

torch.manual_seed(0)

# The function calls pop.get('X'), so pop must be a dict-like object
# with at least an 'X' key
pop = {
    'X': torch.randn(2, 4)
}

ARGS = {
    'pop': pop
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 2, dtype family float, shape (2, 4) — shape (2, 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
default_termination Ran
ran; our contract draft was wrong, not the code
msu-coinlab/pymoo/pymoo/core/algorithm.py
code served (permissive licence) · get_code("b04755c45bc26c0d")
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 DefaultMultiObjectiveTermination. 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.

from pymoo.core.problem import Problem

class StandInProblem(Problem):
    def __init__(self, n_obj):
        self.n_obj = n_obj
        self.n_var = 2
        self.n_ieq_constr = 0
        self.n_eq_constr = 0
        super().__init__(n_var=self.n_var, n_obj=self.n_obj)
    
    def _evaluate(self, x, out, *args, **kwargs):
        out["F"] = x[:, :self.n_obj]

problem_multi = StandInProblem(n_obj=3)
problem_single = StandInProblem(n_obj=1)

ARGS = {
    "problem": problem_multi
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pymoo — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DefaultMultiObjectiveTermination — a DefaultMultiObjectiveTermination output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DefaultMultiObjectiveTermination output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
find_outliers_upper_tail Ran
ran, honoured the contract we drafted
msu-coinlab/pymoo/pymoo/core/decision_making.py
code served (permissive licence) · get_code("dbd4210d0d367d05")
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 int, shape (1,) 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

# Create a sample numpy array with some outliers and normal values
np.random.seed(0)
mu = np.array([1.0, 1.2, 0.9, 1.1, 5.0, 1.3, 0.8, 6.2], dtype=np.float64)

ARGS = {
    'mu': mu
}
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 int, shape (1,) — shape (1,) 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
gen_rand_points Ran
ran on a synthesized input
wjmaddox/mtgp_sampler/hogp_experiments/utils.py
code served (permissive licence) · get_code("fcdd19ca76f3859a")
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 Tensor, ndim 2, dtype family float, shape (2, 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 torch

torch.manual_seed(0)

# bounds should be a tensor with shape (2, d) where d is the number of dimensions
# bounds[0] is the lower bound, bounds[1] is the upper bound
bounds = torch.tensor([[0.0, -5.0, 10.0, 2.0],
                       [1.0, 5.0, 20.0, 8.0]])

# num_samples is an integer specifying how many random points to generate
num_samples = 2

ARGS = {
    "bounds": bounds,
    "num_samples": num_samples
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
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 2, dtype family float, shape (2, 4) — shape (2, 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
generate_initial_data Ran
ran on a synthesized input
wjmaddox/mtgp_sampler/mtgp_experiments/mobo_utils.py
code served (permissive licence) · get_code("dc89546ae499f50a")
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 torch
import torch.nn as nn
from botorch.utils.sampling import draw_sobol_samples

torch.manual_seed(0)

class MockProblem:
    """Stand-in problem class that implements required interface."""
    def __init__(self):
        # bounds should be shape (2, d) where d is dimension
        self.bounds = torch.tensor([[0.0, 0.0, 0.0, 0.0],
                                     [1.0, 1.0, 1.0, 1.0]])
        self.d = 4
    
    def __call__(self, x):
        """Evaluate objective function. x shape: (n, d), returns (n, 1)"""
        # Simple sum of squares as objective
        return (x ** 2).sum(dim=-1, keepdim=True)
    
    def evaluate_slack(self, x):
        """Evaluate constraint slack. x shape: (n, d), returns (n, m) where m is num constraints"""
        # Create 2 dummy constraints
        # Constraint 1: x[0] < 0.5
        # Constraint 2: x[1] < 0.5
        c1 = 0.5 - x[:, 0:1]  # shape (n, 1)
        c2 = 0.5 - x[:, 1:2]  # shape (n, 1)
        return torch.cat([c1, c2], dim=-1)  # shape (n, 2)

problem = MockProblem()

ARGS = {
    'problem': problem,
    'n': 2,
    'method': 'sobol'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
botorch, torch — 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
optimize_acqf_and_get_candidate Ran
ran on a synthesized input
wjmaddox/mtgp_sampler/contextualbo_experiments/contextual_full.py
code served (permissive licence) · get_code("cf6ec1288cd5c5c2")
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 Tensor, ndim 2, dtype family float, shape (2, 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 torch
import torch.nn as nn
from botorch.models import SingleTaskGP
from botorch.acquisition import qExpectedImprovement
from gpytorch.mlls import ExactMarginalLogLikelihood

torch.manual_seed(0)

# Create a simple mock acquisition function
# We need to create actual BoTorch objects for this to work properly
train_X = torch.rand(8, 4)
train_Y = torch.rand(8, 1)

model = SingleTaskGP(train_X, train_Y)
likelihood = ExactMarginalLogLikelihood(model.likelihood, model)

acq_func = qExpectedImprovement(
    model=model,
    best_f=train_Y.max(),
    sampler=None,
)

bounds = torch.stack([
    torch.zeros(4),
    torch.ones(4)
])

batch_size = 2

ARGS = {
    "acq_func": acq_func,
    "bounds": bounds,
    "batch_size": batch_size,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
botorch, gpytorch, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 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
prepare_data Ran
ran on a synthesized input
wjmaddox/mtgp_sampler/hogp_experiments/data.py
code served (permissive licence) · get_code("fdbd5f42a8ca30e4")
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 torch
import numpy as np
from botorch.acquisition.objective import GenericMCObjective

torch.manual_seed(0)

ARGS = {
    "problem": "environmental",
    "s_size": 3,
    "t_size": 4,
    "device": torch.device("cpu"),
    "dtype": torch.float32,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
botorch, fbc, gym_interf, numpy, pde, torch — 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
stats_avg_nevals Ran
ran; our contract draft was wrong, not the code
msu-coinlab/pymoo/pymoo/algorithms/hyperparameters.py
code served (permissive licence) · get_code("3c81f0994213bd5b")
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 dict. 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

class MockEvaluator:
    def __init__(self, n_eval):
        self.n_eval = n_eval

class MockAlgorithm:
    def __init__(self, evaluator):
        self.evaluator = evaluator

class MockResult:
    def __init__(self, n_eval):
        self.algorithm = MockAlgorithm(MockEvaluator(n_eval))

rets = [
    MockResult(n_eval=100),
    MockResult(n_eval=200),
    MockResult(n_eval=300),
]

ARGS = {
    'rets': rets
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
stats_single_objective_mean Ran
ran; our contract draft was wrong, not the code
msu-coinlab/pymoo/pymoo/algorithms/hyperparameters.py
code served (permissive licence) · get_code("0299b2bbd2a03fc2")
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 dict. 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

class ReturnObject:
    def __init__(self, F, G, H):
        self.F = F
        self.G = G
        self.H = H

# Create sample return objects with distinct shapes
ret1 = ReturnObject(
    F=np.array([1.0, 2.0, 3.0, 4.0]),
    G=np.array([0.1, 0.2, 0.3, 0.4]),
    H=np.array([10.0, 20.0, 30.0, 40.0])
)

ret2 = ReturnObject(
    F=np.array([5.0, 6.0, 7.0, 8.0]),
    G=np.array([0.5, 0.6, 0.7, 0.8]),
    H=np.array([50.0, 60.0, 70.0, 80.0])
)

rets = [ret1, ret2]

ARGS = {
    "rets": rets
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not 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
str2bool Ran
ran, violated the contract we drafted
this paper's copy was not recorded; identical code first harvested from sajadn/Exemplar-VAE
pointer only · get_code("7c508037b40522af")
How it ran

The body of this sample is withheld: this paper's copy of the code was not recorded (its link names no repository or source path), so no licence was read for it. 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.

to_float Ran
ran on a synthesized input
msu-coinlab/pymoo/pymoo/core/duplicate.py
code served (permissive licence) · get_code("6485142c167f898b")
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 float, ndim 0, dtype family float, shape () 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

ARGS = {
    "val": True
}
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 float, ndim 0, dtype family float, shape () — shape () 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
to_hash Ran
ran on a synthesized input
msu-coinlab/pymoo/pymoo/core/duplicate.py
code served (permissive licence) · get_code("1e8fc99e292bad09")
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 int, ndim 0, dtype family int, shape () 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
import numpy as np

torch.manual_seed(0)

# The function to_hash takes a parameter x and attempts to hash it
# It first tries hash(x), then falls back to hash(str(x))
# So x can be any hashable type or something that can be converted to string

# Test with various types that can be hashed or converted to string
hashable_int = 42
hashable_str = "test_string"
hashable_tuple = (1, 2, 3)
hashable_float = 3.14
non_hashable_list = [1, 2, 3]  # will fall back to str()
small_tensor = torch.tensor([1.0, 2.0, 3.0, 4.0])  # will fall back to str()
numpy_array = np.array([1, 2, 3, 4])  # will fall back to str()

# The function only needs one argument x
# Using a hashable type for demonstration
ARGS = {
    'x': hashable_int
}
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 int, ndim 0, dtype family int, shape () — shape () 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
calc_cv Not yet run
unverified (harvested, no recorded run)
msu-coinlab/pymoo/pymoo/core/individual.py
code served (permissive licence) · get_code("05e60ce5f589dcbe")
How it ran

no invocation recorded.

construct_acqf Not yet run
unverified (harvested, no recorded run)
wjmaddox/mtgp_sampler/contextualbo_experiments/cbo_experiment.py
code served (permissive licence) · get_code("4e8a410bff1b8df8")
How it ran

no invocation recorded.

create Not yet run
unverified (harvested, no recorded run)
msu-coinlab/pymoo/pymoo/algorithms/hyperparameters.py
code served (permissive licence) · get_code("a7040e3e99b92e1b")
How it ran

no invocation recorded.

env_cfun Not yet run
unverified (harvested, no recorded run)
wjmaddox/mtgp_sampler/hogp_experiments/data.py
code served (permissive licence) · get_code("444ab21c53e16453")
How it ran

no invocation recorded.

optimize_acqf_and_get_candidate Not yet run
unverified (harvested, no recorded run)
wjmaddox/mtgp_sampler/contextualbo_experiments/cbo_experiment.py
code served (permissive licence) · get_code("7cd6031f32f7d8a4")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 distinct functions with an identity, 6 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 1 the same month, 6 later) and 12 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.

FunctionAlso present inEarliest-datedOthers named
str2bool 175 other papers
32 dated earlier, 4 the same month, 139 later · 2 only as an assembly brick
1406.6247 (2014-06)
Recurrent Models of Visual Attention
1603.09382 (2016-03)
Deep Networks with Stochastic Depth
1710.10196 (2017-10)
Progressive Growing of GANs for Improved Quality, Stability, and Variation
and 172 more not named here
create 1 other paper
1 later
2401.15335 (2024-01)
L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks
default_termination 1 other paper
1 later
2401.15335 (2024-01)
L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks
find_outliers_upper_tail 1 other paper
1 later
2401.15335 (2024-01)
L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks
stats_avg_nevals 1 other paper
1 later
2401.15335 (2024-01)
L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks
stats_single_objective_mean 1 other paper
1 later
2401.15335 (2024-01)
L-AutoDA: Leveraging Large Language Models for Automated Decision-based Adversarial Attacks

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

Bayesian Optimization is a sample-efficient black-box optimization procedure that is typically applied to problems with a small number of independent objectives. However, in practice we often wish to optimize objectives defined over many correlated outcomes (or "tasks"). For example, network operators may want to optimize the coverage of a cell tower network across a dense grid of locations. Similarly, engineers may seek to balance the performance of a robot across dozens of different environments via constrained or robust optimization. However, the Gaussian Process (GP) models typically used as probabilistic surrogates for multitask Bayesian Optimization scale poorly with the number of outcomes, which greatly limitis their applicability. We devise an efficient technique for exact multitask GP sampling that combines exploiting Kronecker structure in the covariance matrices with Matheron's identity, allowing us to perform Bayesian Optimization using exact multi-task GP models with tens of thousands of correlated outputs. In doing so, we achieve substantial improvements in sample efficiency compared to existing approaches that only model aggregate functions of the outcomes. We demonstrate how this unlocks a new class of applications for Bayesian Optimization across a range of tasks in science and engineering, including optimizing interference patterns of an optical interferometer with more than 65,000 outputs.

For agents

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

get_harvested_code_for_paper("2106.12997")
get_code_for_paper("2106.12997")
have("2106.12997")

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

curl https://syntology.ai/api/ran/2106.12997.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.12997.svg)](https://syntology.ai/paper/2106.12997)

Connect an agent — have() is free.