SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.04646 · NeurIPS · 2022

Minimax Optimal Algorithms for Fixed-Budget Best Arm Identification

Taira Tsuchiya, Junya Honda, Junpei Komiyama

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 2 failures of our instrument; 2 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/2206.04646.json · badge: /api/ran/2206.04646.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
tsuchhiii/fixed-budget-bai canonical (classifier label)
classifier basis: classifier_2025
7 ran · 2 no recorded run
FunctionStatusWhere it lives
OptNN Ran
ran on a synthesized input · constructed an object; no result was computed
tsuchhiii/fixed-budget-bai/pe_algorithms/mab/optnn.py
pointer only (licence: NONE) · get_code("aeb5a4f641b1e79f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tsuchhiii/fixed-budget-bai when it was checked. 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.

PolicyNet Ran
ran on a synthesized input
tsuchhiii/fixed-budget-bai/pe_algorithms/mab/optnn.py
pointer only (licence: NONE) · get_code("a27deb6b78901563")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tsuchhiii/fixed-budget-bai when it was checked. 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.

Uniform Ran
ran on a synthesized input
tsuchhiii/fixed-budget-bai/pe_algorithms/mab/optnn.py
pointer only (licence: NONE) · get_code("5cf43ffa7f2e8c99")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tsuchhiii/fixed-budget-bai when it was checked. 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.

change_name_for_plot Ran
ran; our contract draft was wrong, not the code
tsuchhiii/fixed-budget-bai/plot_pe.py
pointer only (licence: NONE) · get_code("8f9478ca6861b06e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tsuchhiii/fixed-budget-bai when it was checked. 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.

compute_total_grad_norm Ran
ran, honoured the contract we drafted
tsuchhiii/fixed-budget-bai/fixed_budget_pjt/train_model_batch.py
pointer only (licence: NONE) · get_code("417be79c0af3781b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tsuchhiii/fixed-budget-bai when it was checked. 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.

compute_total_param_norm Ran
ran, honoured the contract we drafted
tsuchhiii/fixed-budget-bai/fixed_budget_pjt/train_model_batch.py
pointer only (licence: NONE) · get_code("ce21debc7413bb09")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tsuchhiii/fixed-budget-bai when it was checked. 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.

step2state Ran
ran; our contract draft was wrong, not the code
tsuchhiii/fixed-budget-bai/fixed_budget_pjt/train_model_batch.py
pointer only (licence: NONE) · get_code("38c3b986e94fbc10")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tsuchhiii/fixed-budget-bai when it was checked. 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.

MABAlgorithm Not yet run
unverified (harvested, no recorded run)
tsuchhiii/fixed-budget-bai/pe_algorithms/mab/optnn.py
pointer only (licence: NONE) · get_code("a75e07b3024bf28b")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tsuchhiii/fixed-budget-bai when it was checked. 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. No invocation recorded.

load_model Not yet run
unverified (harvested, no recorded run)
tsuchhiii/fixed-budget-bai/pe_algorithms/mab/optnn.py
pointer only (licence: NONE) · get_code("9c9714cdfb608340")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, tsuchhiii/fixed-budget-bai when it was checked. 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. No invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 9 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 consider the fixed-budget best arm identification problem where the goal is to find the arm of the largest mean with a fixed number of samples. It is known that the probability of misidentifying the best arm is exponentially small to the number of rounds. However, limited characterizations have been discussed on the rate (exponent) of this value. In this paper, we characterize the minimax optimal rate as a result of an optimization over all possible parameters. We introduce two rates, R go and R go ∞ , corresponding to lower bounds on the probability of misidentification, each of which is associated with a proposed algorithm. The rate R go is associated with R go -tracking, which can be efficiently implemented by a neural network and is shown to outperform existing algorithms. However, this rate requires a nontrivial condition to be achievable. To address this issue, we introduce the second rate R go ∞ . We show that this rate is indeed achievable by introducing a conceptual algorithm called delayed optimal tracking (DOT). 1 We use I * = I * (P ) ⊂ [K] as the set of best arms and i * = i * (P ) ∈ I * (P ) as one of them (ties are broken in an arbitrary way). These differences do not matter much in this paper. 2 See Section 1.3 regarding the related work on BAI and R&S.

For agents

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

get_harvested_code_for_paper("2206.04646")
get_code_for_paper("2206.04646")
have("2206.04646")

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

curl https://syntology.ai/api/ran/2206.04646.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.04646.svg)](https://syntology.ai/paper/2206.04646)

Connect an agent — have() is free.