Metraipolis › archive › dc_edebdeff8452

Stabilizing Performative Feedback Loops with Minimal Model Deployments — arXiv:2609.14065

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.14065
License (as archived)
CC0-1.0
Archived
2026-10-15T23:48:43.842Z
SHA-256 of the archived text
5f036465e4f6beee231f24bbdedb37e045f94879aa17318b66f9a85bfb3257cb
Stable URL of this page
https://metraipolis.com/documento/dc_edebdeff8452

How to cite

Stabilizing Performative Feedback Loops with Minimal Model Deployments — arXiv:2609.14065 — arXiv (en), https://arxiv.org/abs/2609.14065 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edebdeff8452 (Metraipolis archive dc_edebdeff8452, sha256 5f036465e4f6beee231f24bbdedb37e045f94879aa17318b66f9a85bfb3257cb)
BibTeX
@misc{dcedebdeff8452,
  title = {Stabilizing Performative Feedback Loops with Minimal Model Deployments — arXiv:2609.14065},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.14065},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edebdeff8452; sha256 5f036465e4f6beee231f24bbdedb37e045f94879aa17318b66f9a85bfb3257cb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.14065. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When algorithmic predictions inform people's decisions, the models we deploy are performative and actively shape the data we see. This feedback loop between algorithms and their broader environments introduces a challenge in the mechanics of social prediction: If different predictive models induce different distributions, is it possible to efficiently learn a prediction rule that is optimal for the distribution that it induces? Formally, this solution concept is known as performative stability. A core challenge in learning a performatively stable predictor is that, unlike supervised learning where distributions are fixed, the learner must deploy different predictors and observe their induced distributions. The main contribution of our work is a new algorithmic procedure that, in the high-accuracy regime, finds a performatively stable model in nearly the minimum number of model deployments without making any assumptions regarding how predictions shape distributions. In particular, our procedure succeeds at finding a randomized performatively stable predictor using exponentially fewer model deployments than prior approaches. Our second main contribution is a structural result showing how this recent randomized notion of stability achieved by our algorithm can be derandomized into a single predictor satisfying the prior deterministic notion if one is willing to assume that the loss is well-conditioned and that performative effects are weak, as in early work in this area. On a technical level, our results come from building on an underexplored technical connection between performative stability and expected variational inequalities.

Tema degli esploratori: economia dei servizi IA (retro-catalogo arXiv: annunci del 2026-09-15 in cs.GT).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Science and Game Theory (cs.GT).
Pagina del lavoro: https://arxiv.org/abs/2609.14065 — 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 2026-10-15T23:17:52.851Z dalla pagina https://arxiv.org/catchup/cs.GT/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).