MétaCan
Menu
Back to cohort
Record W3007722162 · doi:10.1109/tsp.2021.3089822

Safe Linear Thompson Sampling With Side Information

2021· preprint· en· W3007722162 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.

Bibliographic record

VenueIEEE Transactions on Signal Processing · 2021
Typepreprint
Languageen
FieldDecision Sciences
TopicAdvanced Bandit Algorithms Research
Canadian institutionsUniversity of British Columbia
FundersOffice of the President, University of California
KeywordsFrequentist inferenceRegretThompson samplingSet (abstract data type)Reliability (semiconductor)Linear programmingMathematicsComputer scienceAlgorithmMathematical optimizationSampling (signal processing)CombinatoricsBayesian probabilityStatisticsBayesian inference

Abstract

fetched live from OpenAlex

The design and performance analysis of bandit algorithms in the presence of stage-wise safety or reliability constraints has recently garnered significant interest. In this work, we consider the linear stochastic bandit problem under additional unknown linear safety constraints that need to be satisfied at each round. For this problem, we present and analyze a new safe algorithm based on linear Thompson Sampling (TS). Our analysis shows that, with high probability, the algorithm chooses actions that are safe at each round and achieve cumulative regret of order <i xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</i> (d <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3/2</sup> log <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1/2</sup> d ·T <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1/2</sup> log <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3/2</sup> T). Remarkably, this matches the regret bound provided by [1], [2] for the standard linear TS algorithm in the absence of safety constraints. Also, our analysis highlights how the inherently randomized nature of the TS selection rule suffices to properly expand the set of safe actions that the algorithm has access to at each round. In particular, we compare this behavior to alternative safe algorithms, which typically require distinct rounds of randomization that are dedicated to learning the unknown constraints.

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)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Scholarly communication, Research integrity
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.912
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.002
Science and technology studies0.0010.000
Scholarly communication0.0020.003
Open science0.0010.000
Research integrity0.0000.002
Insufficient payload (model declined to judge)0.0010.000

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 head0.141
GPT teacher head0.418
Teacher spread0.276 · 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