MétaCan
Menu
Back to cohort
Record W2095762034 · doi:10.5555/1577069.1577089

Online Learning with Sample Path Constraints

2009· article· en· W2095762034 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

VenueDSpace@MIT (Massachusetts Institute of Technology) · 2009
Typearticle
Languageen
FieldDecision Sciences
TopicAdvanced Bandit Algorithms Research
Canadian institutionsMcGill University
Fundersnot available
KeywordsHindsight biasPath (computing)HeuristicMathematical optimizationConvex hullSample (material)Constraint (computer-aided design)Computer scienceDecision makerFunction (biology)Measure (data warehouse)Term (time)MathematicsRegular polygonOperations researchData miningPsychology

Abstract

fetched live from OpenAlex

We study online learning when the objective of the decision maker is to maximize her long-term average reward subject to certain sample path average constraints. We define the reward-in-hindsight as the highest reward the decision maker could have achieved, while satisfying the constraints, had she known Nature’s choices in advance. We show that in general the reward-in-hindsight is not attainable. The convex hull of the reward-in-hindsight function is, however, attainable. For the important case of a single constraint, the convex hull turns out to be the highest attainable function. Using a calibrated forecasting rule, we provide an explicit strategy that attains this convex hull. We also measure the performance of heuristic methods based on non-calibrated forecasters in experiments involving a CPU power management problem. 1.

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)0.001
metaresearch head score (Gemma)0.009
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMetaresearch, Meta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Other design · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.947
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.009
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0020.004
Science and technology studies0.0000.002
Scholarly communication0.0000.001
Open science0.0020.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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 head0.049
GPT teacher head0.362
Teacher spread0.314 · 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