MétaCan
Menu
Back to cohort
Record W4312881858 · doi:10.1109/tit.2022.3222231

Almost Optimal Variance-Constrained Best Arm Identification

2022· article· en· W4312881858 on OpenAlexaff
Yunlong Hou, Vincent Y. F. Tan, Zixin Zhong

Bibliographic record

VenueIEEE Transactions on Information Theory · 2022
Typearticle
Languageen
FieldComputer Science
TopicMachine Learning and Algorithms
Canadian institutionsUniversity of Alberta
FundersMinistry of Education - SingaporeNational Research Foundation Singapore
KeywordsIdentification (biology)Computer scienceVariance (accounting)AlgorithmMathematical optimizationStatisticsMathematics

Abstract

fetched live from OpenAlex

We design and analyze Variance-Aware-Lower and Upper Confidence Bound (VA-LUCB), a parameter-free algorithm, for identifying the best arm under the fixed-confidence setup and under a stringent constraint that the variance of the chosen arm is strictly smaller than a given threshold. An upper bound on VA-LUCB’s sample complexity is shown to be characterized by a fundamental variance-aware hardness quantity$H_{\mathrm {VA}}$. By proving an information-theoretic lower bound, we show that sample complexity of VA-LUCB is optimal up to a factor logarithmic in$H_{\mathrm {VA}}$. Extensive experiments corroborate the dependence of the sample complexity on the various terms in$H_{\mathrm {VA}}$. By comparing VA-LUCB’s empirical performance to a close competitor RiskAverse-UCB-BAI by David et al. (2018) our experiments suggest that VA-LUCB has the lowest sample complexity for this class of risk-constrained best arm identification problems, especially for the riskiest instances.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.007
metaresearch head score (Gemma)0.052
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Theoretical or conceptual · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.007
Threshold uncertainty score0.039

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0070.052
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0030.002
Bibliometrics0.0020.002
Science and technology studies0.0010.002
Scholarly communication0.0040.004
Open science0.0040.005
Research integrity0.0040.004
Insufficient payload (model declined to judge)0.0070.003

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.008
GPT teacher head0.228
Teacher spread0.221 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designTheoretical or conceptual
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations8
Published2022
Admission routes1
Has abstractyes

Explore more

Same venueIEEE Transactions on Information TheorySame topicMachine Learning and AlgorithmsFrench-language works237,207