MétaCan
Menu
Back to cohort
Record W4283778953 · doi:10.1111/poms.13786

Bayesian dithering for learning: Asymptotically optimal policies in dynamic pricing

2022· article· en· W4283778953 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

VenueProduction and Operations Management · 2022
Typearticle
Languageen
FieldDecision Sciences
TopicAdvanced Bandit Algorithms Research
Canadian institutionsUniversity of British Columbia
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsDitherRegretUpper and lower boundsAsymptotically optimal algorithmMathematical optimizationComputer scienceLogarithmDynamic pricingParametric statisticsBayesian probabilityOrder (exchange)Set (abstract data type)MathematicsEconomicsArtificial intelligenceMachine learningMicroeconomicsStatisticsFinance

Abstract

fetched live from OpenAlex

We consider a dynamic pricing and learning problem where a seller prices multiple products and learns from sales data about unknown demand. We study the parametric demand model in a Bayesian setting. To avoid the classical problem of incomplete learning, we propose dithering policies under which prices are probabilistically selected in a neighborhood surrounding the myopic optimal price. By analyzing the effect of dithering in facilitating learning, we establish regret upper bounds for three typical settings of demand model. We show that the dithering policy achieves an upper bound of order <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" overflow="scroll"> <mml:semantics definitionURL="" encoding=""> <mml:mrow> <mml:mi>log</mml:mi> <mml:mi>T</mml:mi> </mml:mrow> <mml:annotation encoding="">$\log T$</mml:annotation> </mml:semantics> </mml:math> when the parameter set is finite. It can be modified to achieve a constant regret bound under an additional assumption. We also prove an upper bound of order <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline" overflow="scroll"> <mml:semantics definitionURL="" encoding=""> <mml:msqrt> <mml:mrow> <mml:mi>T</mml:mi> <mml:mi>log</mml:mi> <mml:mi>T</mml:mi> </mml:mrow> </mml:msqrt> <mml:annotation encoding="">$\sqrt {T\log T}$</mml:annotation> </mml:semantics> </mml:math> when the parameter set is compact and convex. Each bound matches (up to a logarithmic factor) the existing lower bound of any pricing policy. In this way, we show that dithering policies achieve asymptotically optimal performance in three different parameter settings, which demonstrates dithering as a unified approach to strike the balance between exploration and exploitation.

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)0.001
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.871
Threshold uncertainty score0.676

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.001
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0010.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
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 head0.044
GPT teacher head0.391
Teacher spread0.346 · 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