MétaCan
Menu
Back to cohort
Record W2952938032 · doi:10.48550/arxiv.1110.6755

PAC-Bayes-Bernstein Inequality for Martingales and its Application to\n Multiarmed Bandits

2011· preprint· W2952938032 on OpenAlexaff
Yevgeny Seldin, Nicolò Cesa‐Bianchi, Peter Auer, François Laviolette, John Shawe‐Taylor

Bibliographic record

VenuearXiv (Cornell University) · 2011
Typepreprint
Language
FieldDecision Sciences
TopicAdvanced Bandit Algorithms Research
Canadian institutionsUniversité Laval
Fundersnot available
KeywordsBayes' theoremComputer scienceInequalityMathematical optimizationInterdependenceArtificial intelligenceMathematicsBayesian probability

Abstract

fetched live from OpenAlex

We develop a new tool for data-dependent analysis of the\nexploration-exploitation trade-off in learning under limited feedback. Our tool\nis based on two main ingredients. The first ingredient is a new concentration\ninequality that makes it possible to control the concentration of weighted\naverages of multiple (possibly uncountably many) simultaneously evolving and\ninterdependent martingales. The second ingredient is an application of this\ninequality to the exploration-exploitation trade-off via importance weighted\nsampling. We apply the new tool to the stochastic multiarmed bandit problem,\nhowever, the main importance of this paper is the development and understanding\nof the new tool rather than improvement of existing algorithms for stochastic\nmultiarmed bandits. In the follow-up work we demonstrate that the new tool can\nimprove over state-of-the-art in structurally richer problems, such as\nstochastic multiarmed bandits with side information (Seldin et al., 2011a).\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.

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)0.011
metaresearch head score (Gemma)0.044
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: Theoretical or conceptual
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.011
Threshold uncertainty score0.061

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0110.044
Meta-epidemiology (narrow)0.0020.001
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0020.002
Science and technology studies0.0010.004
Scholarly communication0.0030.006
Open science0.0030.004
Research integrity0.0030.007
Insufficient payload (model declined to judge)0.0060.001

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 head0.278
GPT teacher head0.327
Teacher spread0.049 · 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
GenreEmpirical

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

Citations0
Published2011
Admission routes1
Has abstractyes

Explore more

Same venuearXiv (Cornell University)Same topicAdvanced Bandit Algorithms ResearchFrench-language works237,207