Metraipolis › archive › dc_66db1ba99d44

Bayes-Consistent Losses for Adaptive Inference in Classification — arXiv:2610.39709

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39709
License (as archived)
CC0-1.0
Archived
2026-11-01T02:27:16.420Z
SHA-256 of the archived text
0e891d7a2727b3461676a2f04e2d29a8e1e4ed5c87a381504195340d7096a9bb
Stable URL of this page
https://metraipolis.com/documento/dc_66db1ba99d44

How to cite

Bayes-Consistent Losses for Adaptive Inference in Classification — arXiv:2610.39709 — arXiv (en), https://arxiv.org/abs/2610.39709 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_66db1ba99d44 (Metraipolis archive dc_66db1ba99d44, sha256 0e891d7a2727b3461676a2f04e2d29a8e1e4ed5c87a381504195340d7096a9bb)
BibTeX
@misc{dc66db1ba99d44,
  title = {Bayes-Consistent Losses for Adaptive Inference in Classification — arXiv:2610.39709},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39709},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_66db1ba99d44; sha256 0e891d7a2727b3461676a2f04e2d29a8e1e4ed5c87a381504195340d7096a9bb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39709. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Adaptive inference systems balance accuracy and inference cost by routing inputs to models with varying capabilities. Although jointly training models and routers is empirically more sample-efficient than training them separately, principled losses for joint training remain underexplored. We address this gap in a classification setting by proposing cost-sensitive hinge losses for jointly training classifiers with single-stage or cascade routers. Single-stage routers directly select a model per input, whereas cascade routers sequentially decide at each stage whether to predict with the current model or defer to the next stage, which uses a more accurate but more costly model. For both settings, we prove linear calibration bounds establishing Bayes consistency: minimizing the hinge risk recovers the Bayes-optimal risk under the target cost-sensitive zero-one loss. Moreover, since routers can require more labeled data to train than classifiers, we propose a novel post-training prediction-powered inference (PPI) procedure that uses unlabeled data to refine a trained single-stage router. Experiments on synthetic and real datasets demonstrate that the proposed hinge losses are effective for joint training and that PPI can correct routing errors when labeled data is scarce.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (stat.ML) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.39709 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-01T02:12:44.311Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).