Metraipolis › archive › dc_017441f7cf93
Performative Prediction with Selective Labels — arXiv:2610.08272
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.08272
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T11:41:41.614Z
- SHA-256 of the archived text
dd7f21c720e5e9e4b4c9ab5ee7fcbc1a7f319c856c9a4e1d93923a490d70650d- Stable URL of this page
https://metraipolis.com/documento/dc_017441f7cf93
How to cite
Performative Prediction with Selective Labels — arXiv:2610.08272 — arXiv (en), https://arxiv.org/abs/2610.08272 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_017441f7cf93 (Metraipolis archive dc_017441f7cf93, sha256 dd7f21c720e5e9e4b4c9ab5ee7fcbc1a7f319c856c9a4e1d93923a490d70650d)
BibTeX
@misc{dc017441f7cf93,
title = {Performative Prediction with Selective Labels — arXiv:2610.08272},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.08272},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_017441f7cf93; sha256 dd7f21c720e5e9e4b4c9ab5ee7fcbc1a7f319c856c9a4e1d93923a490d70650d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08272. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many social applications of machine learning exhibit performative effects: population behavior changes in response to deployed models. Performative prediction studies this interaction through a distribution map that relates each model to the population distribution it induces. One of the main results in this framework showed that repeated risk minimization (RRM), which updates models by retraining on the most recent data, can converge to a stable model that minimizes risk on its own induced distribution. However, existing analyses typically assume access to the complete distributions of features and labels after model deployment, ignoring the possibility of selective labels: observing labels only for the accepted subset of the population. In this work, we formalize performative prediction with selective labels and show that retraining only on observed data can misguide the retraining procedure and undermine the guarantees of convergence to a stable solution. We then propose a worst-case objective based on knowledge of a confidence interval on the probability of a positive label. Applying RRM to this objective permits us to remain within a bounded distance to the true stable point. Under a sensitivity assumption on the conditional label distribution, we further show how previously accepted data can tighten these confidence intervals over time. Experiments in a lending application with fairness regularization show that our robust optimization approach closely matches the performance of RRM with complete label access. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.08272 — 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 2026-10-07T11:19:24.820Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).