Optimally-Smooth Adaptive Boosting and Application to Agnostic Learning
Bibliographic record
Abstract
We describe a new boosting algorithm that is the first such algorithm to be both smooth and adaptive. These two features make possible performance improvements for many learning tasks whose solutions use a boosting technique. The boosting approach was originally suggested for the standard PAC model; we analyze possible applications of boosting in the context of agnostic learning, which is more realistic than the PAC model. We derive a lower bound for the final error achievable by boosting in the agnostic model and show that our algorithm actually achieves that accuracy (within a constant factor). We note that the idea of applying boosting in the agnostic model was first suggested by Ben-David, Long and Mansour and the solution they give is improved in the present paper. The accuracy we achieve is exponentially better with respect to the standard agnostic accuracy parameter β. We also describe the construction of a boosting “tandem ” whose asymptotic number of iterations is the lowest possible (in both γ and ε) and whose smoothness is optimal in terms of Õ. This allows adaptively solving problems whose solution is based on smooth boosting (like noise tolerant boosting and DNF membership learning), while preserving the original (non-adaptive) solution’s complexity. 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.
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 | 0.003 | 0.008 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.002 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".