Metraipolis › archive › dc_358fdc494cc8

The Lagrangian Structure of Cost-Penalized Active Feature Acquisition — arXiv:2610.21919

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21919
License (as archived)
CC0-1.0
Archived
2026-10-16T10:24:42.521Z
SHA-256 of the archived text
9e87ae5fed9d4fe2c50d2f432dd15ed1df799815466513d35556b40984e49457
Stable URL of this page
https://metraipolis.com/documento/dc_358fdc494cc8

How to cite

The Lagrangian Structure of Cost-Penalized Active Feature Acquisition — arXiv:2610.21919 — arXiv (en), https://arxiv.org/abs/2610.21919 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_358fdc494cc8 (Metraipolis archive dc_358fdc494cc8, sha256 9e87ae5fed9d4fe2c50d2f432dd15ed1df799815466513d35556b40984e49457)
BibTeX
@misc{dc358fdc494cc8,
  title = {The Lagrangian Structure of Cost-Penalized Active Feature Acquisition — arXiv:2610.21919},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21919},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_358fdc494cc8; sha256 9e87ae5fed9d4fe2c50d2f432dd15ed1df799815466513d35556b40984e49457},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21919. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Active Feature Acquisition (AFA) sequentially selects features to maximize predictive accuracy under an acquisition budget. A natural heuristic greedily maximizes Expected Information Gain minus a cost penalty, EIG(j|x_S)-lam*c_j (EIG-Cost), but its theoretical guarantees are unclear. We provide an a-posteriori certificate decomposing the gap to the optimal hard-budget policy into a budget-slack term and a greedy-suboptimality term Del_lam. The certificate is computable when the penalized optimum is tractable; on small heterogeneous-cost instances, we verify it exactly, finding Del_lam near zero across 4,000 solved cases. On the large clinical task, Del_lam is not computable, so the decomposition is diagnostic rather than a numerical guarantee. Our analysis identifies EIG-Cost as one-step greedy optimization of the Lagrangian relaxation of expected-cost AFA, with lam as its dual multiplier. For equal costs, we prove Del_lam <= exp(-gam*I(Y;X_[d])), where gam is the submodularity ratio, yielding a structural guarantee in the near-submodular regime. Supporting results establish an adaptive chain-rule identity showing that cumulative stepwise EIG optimizes transcript information, and prove that A -> I(Y;X_A) need not be submodular, even for jointly Gaussian variables. This rules out a direct Nemhauser-Wolsey-Fisher bound; naive Bayes restores submodularity. We also bound the randomization gap between hard-budget and expected-cost optima, analyze sensitivity to dual-multiplier error under local smoothness, and derive a conditional CVAE generator-shift bound given a bound on forward predictive KL. We treat this KL as a diagnostic quantity, not as a transform of training loss. Experiments cover synthetic Gaussian settings, AFA benchmarks, and clinical differential diagnosis on MIMIC-IV. On MIMIC-IV, EIG-Cost achieves macro-F1 0.180 +/- 0.012 at a $30 budget, using 6.6% of full-panel cost.

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/2610.21919 — 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 2026-10-16T08:48:02.771Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).