Metraipolis › archive › dc_43fb73e4715d

Reliability-Aware Checkpoint Selection for Domain Generalization — arXiv:2609.39934

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39934
License (as archived)
CC0-1.0
Archived
2026-10-07T13:46:49.327Z
SHA-256 of the archived text
a4baf08bb65be8bd7c98d0d3820647eda12125cd4979ac2922998b2d58401f50
Stable URL of this page
https://metraipolis.com/documento/dc_43fb73e4715d

How to cite

Reliability-Aware Checkpoint Selection for Domain Generalization — arXiv:2609.39934 — arXiv (en), https://arxiv.org/abs/2609.39934 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_43fb73e4715d (Metraipolis archive dc_43fb73e4715d, sha256 a4baf08bb65be8bd7c98d0d3820647eda12125cd4979ac2922998b2d58401f50)
BibTeX
@misc{dc43fb73e4715d,
  title = {Reliability-Aware Checkpoint Selection for Domain Generalization — arXiv:2609.39934},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39934},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_43fb73e4715d; sha256 a4baf08bb65be8bd7c98d0d3820647eda12125cd4979ac2922998b2d58401f50},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39934. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Checkpoint selection in domain generalization often relies on source-validation accuracy, yet the selected checkpoint need not provide reliable probabilities on unseen target domains. Source-target distribution shifts can alter accuracy rankings, while accuracy alone does not measure predictive probability quality. We identify an empirical selection opportunity within fixed training trajectories: reselecting among checkpoints with near-optimal source accuracy can improve mean target probability quality with small observed changes in mean target accuracy. We study accuracy-constrained reliability selection (AC), which retains checkpoints within a tolerance of the best source-validation accuracy and ranks them by source reliability. Our reference rule aggregates within-set normalized negative log-likelihood (NLL) and class-wise calibration error (CwECE) using $D_\infty$. AC uses no target data and requires neither additional training nor weight averaging. We evaluate five domain generalization training algorithms on three benchmarks, using PACS to develop the objectives and a 0.5-percentage-point tolerance. In exploratory aggregation comparisons on 360 OfficeHome and TerraIncognita runs, the reference rule reduces mean target soft-bin squared-gap ECE and CwECE by 0.240% and 0.182%, respectively, and NLL by 0.030 relative to Source-Acc. Mean target accuracy changes by +0.213 percentage points. These results identify opportunities for reliability-aware reselection, while the additional benefit of joint over single-objective ranking remains unresolved.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.39934 — 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 2026-10-07T13:18:10.492Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).