SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.08166 · 2021

Automatic Termination for Hyperparameter Optimization

arXiv · PDF · Open in the Atlas

Code that ran

6 of 6 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; 5 failures of our instrument; 0 no recorded run), measured 2026-11-21; 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/2104.08166.json · badge: /api/ran/2104.08166.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
amazon-research/bo-early-stopping canonical (classifier label)
classifier basis: census
6 ran · 0 no recorded run
FunctionStatusWhere it lives
extract_algo Ran
ran; our contract draft was wrong, not the code
amazon-research/bo-early-stopping/src/util.py
code served (permissive licence) · get_code("14b7afc993448c17")
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 str. 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 tempfile
import os

# Create temporary CSV file paths for testing
temp_dir = tempfile.gettempdir()

# Test case 1: XGB in path
xgb_csv_path = os.path.join(temp_dir, "results_XGB_model.csv")

# Test case 2: fcnet in path
fcnet_csv_path = os.path.join(temp_dir, "fcnet_results.csv")

# Test case 3: hpobench in path
hpobench_csv_path = os.path.join(temp_dir, "hpobench_benchmark.csv")

# Test case 4: nas201 in path
nas201_csv_path = os.path.join(temp_dir, "nas201_search.csv")

# Test case 5: no matching keyword (should return 'RF')
other_csv_path = os.path.join(temp_dir, "generic_results.csv")

# Use the XGB path as the main test case
ARGS = {
    'csv_path': xgb_csv_path
}
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 str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str 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
extract_metric Ran
ran, honoured the contract we drafted
amazon-research/bo-early-stopping/bin/start_gap_estimation.py
code served (permissive licence) · get_code("99523aea225a3952")
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 list, 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

torch.manual_seed(0)

# The function iterates over validation_metrics_dict and checks each dictionary
# for 'error' key, falling back to 'rmse' key
# So we need a list of dictionaries, each containing either 'error' or 'rmse'

validation_metrics_dict = [
    {'error': 0.5},
    {'rmse': 0.3},
    {'error': 0.2},
    {'rmse': 0.7},
]

ARGS = {
    'validation_metrics_dict': validation_metrics_dict
}
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 list, ndim 1, dtype family float — a list 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_overfit_iter Ran
ran; our contract draft was wrong, not the code
amazon-research/bo-early-stopping/bin/gen_csv.py
code served (permissive licence) · get_code("be1a632e2b500b21")
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 pandas as pd
import numpy as np

# Create a sample dataframe with the required columns
# The function expects 'iteration' and 'incumbent_test_metric' columns
data = {
    'iteration': [1, 5, 10, 15, 20, 25, 30, 35, 40, 45],
    'incumbent_test_metric': [0.5, 0.45, 0.42, 0.40, 0.38, 0.36, 0.35, 0.37, 0.40, 0.45]
}
df = pd.DataFrame(data)

ARGS = {
    'df': df
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — 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
get_stop_info_conv Ran
ran; our contract draft was wrong, not the code
amazon-research/bo-early-stopping/src/stop_methods.py
code served (permissive licence) · get_code("7f22afc4b599f122")
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 pandas as pd
import numpy as np

# Create a sample dataframe with the required columns
# The function iterates through rows and accesses specific columns
data = {
    'iteration': [1, 2, 3, 4, 5, 6, 7, 8, 9, 10],
    'incumbent_val_metric': [0.5, 0.45, 0.42, 0.41, 0.40, 0.40, 0.40, 0.40, 0.40, 0.39],
    'incumbent_test_metric': [0.52, 0.47, 0.44, 0.43, 0.41, 0.41, 0.41, 0.41, 0.41, 0.40],
    'total_train_time': [10, 20, 30, 40, 50, 60, 70, 80, 90, 100]
}

df = pd.DataFrame(data)

ARGS = {
    'df': df,
    'k': 30,
    'nas': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — 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_stop_info_ours Ran
ran; our contract draft was wrong, not the code
amazon-research/bo-early-stopping/src/stop_methods.py
code served (permissive licence) · get_code("645b1912976d2844")
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 pandas as pd
import numpy as np

# Create a minimal DataFrame that satisfies the function's requirements
data = {
    'iteration': [1, 2, 3, 4, 5],
    'incumbent_val_metric': [0.9, 0.85, 0.80, 0.75, 0.70],
    'incumbent_test_metric': [0.88, 0.83, 0.78, 0.73, 0.68],
    'incumbent_val_metric': [0.9, 0.85, 0.80, 0.75, 0.70],
    'total_train_time': [10.0, 20.0, 30.0, 40.0, 50.0],
    'regret_bound': [0.5, 0.4, 0.3, 0.2, 0.1],
    'true_regret': [0.48, 0.38, 0.28, 0.18, 0.08],
    'incumbent_std': [0.1, 0.095, 0.09, 0.085, 0.08],
}

df = pd.DataFrame(data)

ARGS = {
    'df': df,
    'decay': 0.21,
    'std': None,
    'use_true_regret': False,
    'nas': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — 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_stop_info_ours_corrected Ran
ran; our contract draft was wrong, not the code
amazon-research/bo-early-stopping/src/stop_methods.py
code served (permissive licence) · get_code("796b91add8ea7c9d")
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 pandas as pd
import numpy as np

# Create a minimal DataFrame with the required columns
data = {
    'iteration': [1, 2, 3, 4, 5],
    'incumbent_val_metric': [0.5, 0.45, 0.42, 0.40, 0.38],
    'incumbent_test_metric': [0.52, 0.47, 0.44, 0.41, 0.39],
    'total_train_time': [10.0, 20.0, 30.0, 40.0, 50.0],
    'regret_bound': [0.5, 0.35, 0.25, 0.15, 0.08],
    'true_regret': [0.48, 0.33, 0.23, 0.13, 0.06],
    'incumbent_std': [0.10, 0.08, 0.06, 0.04, 0.02]
}

df = pd.DataFrame(data)

ARGS = {
    'df': df,
    'decay': 0.21,
    'std': None,
    'use_true_regret': False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — 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 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 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 6 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 2026-11-21.

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 (BO) is a widely popular approach for the hyperparameter optimization (HPO) in machine learning. At its core, BO iteratively evaluates promising configurations until a user-defined budget, such as wall-clock time or number of iterations, is exhausted. While the final performance after tuning heavily depends on the provided budget, it is hard to pre-specify an optimal value in advance. In this work, we propose an effective and intuitive termination criterion for BO that automatically stops the procedure if it is sufficiently close to the global optimum. Our key insight is that the discrepancy between the true objective (predictive performance on test data) and the computable target (validation performance) suggests stopping once the suboptimality in optimizing the target is dominated by the statistical estimation error. Across an extensive range of real-world HPO problems and baselines, we show that our termination criterion achieves a better trade-off between the test performance and optimization time. Additionally, we find that overfitting may occur in the context of HPO, which is arguably an overlooked problem in the literature, and show how our termination criterion helps to mitigate this phenomenon on both small and large datasets.

For agents

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

get_harvested_code_for_paper("2104.08166")
get_code_for_paper("2104.08166")
have("2104.08166")

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

curl https://syntology.ai/api/ran/2104.08166.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.08166.svg)](https://syntology.ai/paper/2104.08166)

Connect an agent — have() is free.