MétaCan
Menu
Back to cohort
Record W4298085585 · doi:10.48550/arxiv.1001.4475

X-Armed Bandits

2010· preprint· en· W4298085585 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

VenuearXiv (Cornell University) · 2010
Typepreprint
Languageen
FieldDecision Sciences
TopicAdvanced Bandit Algorithms Research
Canadian institutionsAthabasca UniversityUniversity of Alberta
FundersAlberta InnovatesCentre National de la Recherche ScientifiqueAgence Nationale de la RechercheNatural Sciences and Engineering Research Council of CanadaInstitut national de recherche en informatique et en automatique (INRIA)
KeywordsComputer science

Abstract

fetched live from OpenAlex

We consider a generalization of stochastic bandits where the set of arms,\n$\\cX$, is allowed to be a generic measurable space and the mean-payoff function\nis "locally Lipschitz" with respect to a dissimilarity function that is known\nto the decision maker. Under this condition we construct an arm selection\npolicy, called HOO (hierarchical optimistic optimization), with improved regret\nbounds compared to previous results for a large class of problems. In\nparticular, our results imply that if $\\cX$ is the unit hypercube in a\nEuclidean space and the mean-payoff function has a finite number of global\nmaxima around which the behavior of the function is locally continuous with a\nknown smoothness degree, then the expected regret of HOO is bounded up to a\nlogarithmic factor by $\\sqrt{n}$, i.e., the rate of growth of the regret is\nindependent of the dimension of the space. We also prove the minimax optimality\nof our algorithm when the dissimilarity is a metric. Our basic strategy has\nquadratic computational complexity as a function of the number of time steps\nand does not rely on the doubling trick. We also introduce a modified strategy,\nwhich relies on the doubling trick but runs in linearithmic time. Both results\nare improvements with respect to previous approaches.\n

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.

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.003
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Research integrity, Insufficient payload (model declined to judge)
Consensus categoriesInsufficient payload (model declined to judge)
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.602
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.003
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.002
Science and technology studies0.0000.001
Scholarly communication0.0000.000
Open science0.0040.004
Research integrity0.0010.003
Insufficient payload (model declined to judge)0.0030.003

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 head0.295
GPT teacher head0.318
Teacher spread0.023 · 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