Robust auctions and uniform convergence
Bibliographic record
Abstract
Our goal is to make progress towards learning auctions from limited access to value distributions.Towards this, we know that VC dimension cannot be used to efficiently obtain the uniform convergence property with respect to the empirical distribution.We show that in fact a more refined tool, the Rademacher Complexity, also requires an exponential number of sample points in the dimension to satisfy uniform convergence.However, given access to approximations of the true value distributions, we show in different settings how to construct auctions that are oblivious to the true distribution, yet yield close to optimal revenue.iii ABR ÉG É Notre objectif est de progresser dans l'apprentissage des enchères à partir d'un accès limité aux distributions de valeurs.À cet égard, nous savons que la dimension VC ne peut pas être utilisée pour obtenir efficacement la propriété de convergence uniforme en ce qui concerne la distribution empirique.Nous montrons qu'un outil plus raffiné, la complexité de Rademacher, requiert également un nombre exponentiel de points d'échantillon dans la dimension pour satisfaire une convergence uniforme.Cependant, étant donné l'accès aux approximations des distributions de la valeur réelle, nous montrons, dans différents contextes, comment construire des enchères inconscientes de la distribution réelle, tout en produisant un revenu proche du revenu optimal.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.012 | 0.075 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.004 |
| Scholarly communication | 0.004 | 0.007 |
| Open science | 0.002 | 0.005 |
| Research integrity | 0.002 | 0.005 |
| Insufficient payload (model declined to judge) | 0.008 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".