Learning Stochastic Majority Votes by Minimizing a PAC-Bayes Generalization Bound
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.
Bibliographic record
Abstract
We investigate a stochastic counterpart of majority votes over finite\nensembles of classifiers, and study its generalization properties. While our\napproach holds for arbitrary distributions, we instantiate it with Dirichlet\ndistributions: this allows for a closed-form and differentiable expression for\nthe expected risk, which then turns the generalization bound into a tractable\ntraining objective. The resulting stochastic majority vote learning algorithm\nachieves state-of-the-art accuracy and benefits from (non-vacuous) tight\ngeneralization bounds, in a series of numerical experiments when compared to\ncompeting algorithms which also minimize PAC-Bayes objectives -- both with\nuninformed (data-independent) and informed (data-dependent) priors.\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.
Full frame distilled prediction
Teacher imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it