Metraipolis › archive › dc_cecabd7617e3

Beyond Fixed Acquisition Functions: Temporal Difference Active Learning for Perturbation Discovery — arXiv:2610.22122

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.22122
License (as archived)
CC0-1.0
Archived
2026-10-16T10:24:48.319Z
SHA-256 of the archived text
b91381640c9ef400b6ab88b2495efeff8019b546ac56da8b95fd5490bfb7e50c
Stable URL of this page
https://metraipolis.com/documento/dc_cecabd7617e3

How to cite

Beyond Fixed Acquisition Functions: Temporal Difference Active Learning for Perturbation Discovery — arXiv:2610.22122 — arXiv (en), https://arxiv.org/abs/2610.22122 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cecabd7617e3 (Metraipolis archive dc_cecabd7617e3, sha256 b91381640c9ef400b6ab88b2495efeff8019b546ac56da8b95fd5490bfb7e50c)
BibTeX
@misc{dccecabd7617e3,
  title = {Beyond Fixed Acquisition Functions: Temporal Difference Active Learning for Perturbation Discovery — arXiv:2610.22122},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22122},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cecabd7617e3; sha256 b91381640c9ef400b6ab88b2495efeff8019b546ac56da8b95fd5490bfb7e50c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22122. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Genetic and drug perturbation screens are important tools for elucidating disease mechanisms and validating therapeutic targets, but experimental costs limit the number of candidates that can be tested. Existing perturbation screening methods typically update the surrogate model with feedback while keeping the acquisition function fixed, limiting their ability to adapt selection to different response landscapes. Experimental feedback reveals current hits and informs subsequent selection by updating candidate predictions, providing a training signal for learning how to select experiments. We formulate budgeted perturbation discovery as a sequential decision problem and propose Temporal Difference Active Learning (TDAL), which learns an acquisition function online through temporal difference learning from a single screening trajectory, accounting for current hits and future discoveries. TDAL uses the Hellinger distance between hit probabilities for unmeasured candidates before and after an experiment to weight successor value, and reuses measured outcomes through leave-batch-out (LBO) to construct virtual transitions and alleviate training data scarcity. Across eight public screens spanning single, double, and triple perturbations under varied experimental configurations, TDAL achieves an average rank of 1.63 among eleven methods and ranks first on four tasks, demonstrating its adaptability across response landscapes.

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/2610.22122 — 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 2026-10-16T08:48:02.794Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).