Metraipolis › archive › dc_11276cb41ed8
Rethinking Learnability in Offline Data-driven Optimization — arXiv:2609.01493
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01493
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:34:23.357Z
- SHA-256 of the archived text
45bcf46179548cb4bc19e4d0cd2d708a77e7fcdeb4bf9087273f993a6177c854- Stable URL of this page
https://metraipolis.com/documento/dc_11276cb41ed8
How to cite
Rethinking Learnability in Offline Data-driven Optimization — arXiv:2609.01493 — arXiv (en), https://arxiv.org/abs/2609.01493 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_11276cb41ed8 (Metraipolis archive dc_11276cb41ed8, sha256 45bcf46179548cb4bc19e4d0cd2d708a77e7fcdeb4bf9087273f993a6177c854)
BibTeX
@misc{dc11276cb41ed8,
title = {Rethinking Learnability in Offline Data-driven Optimization — arXiv:2609.01493},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01493},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_11276cb41ed8; sha256 45bcf46179548cb4bc19e4d0cd2d708a77e7fcdeb4bf9087273f993a6177c854},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01493. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Black-Box Optimization (BBO) has broad applications, while traditional algorithms such as evolutionary algorithms and Bayesian optimization face efficiency challenges as real-world BBO problems grow increasingly complex. Data-driven optimization has been the most popular paradigm to improve the efficiency of BBO, by learning from data. Offline data-driven optimization seeks high-quality solutions using only a fixed set of previous evaluations, attracting substantial attention because it requires no additional online evaluations. Many offline optimization methods have been proposed, but a fundamental question remains unanswered: what learnability is sufficient for offline optimization? Prior theoretical studies show that Probably Approximately Correct (PAC) learnability is insufficient, as the optimal region may remain poorly learned even when most regions are well learned. In this paper, we propose algorithm-dependent learnability, which requires accuracy only on the optimizer's trajectory. We prove that its value-query form is sufficient for representative discrete settings, including greedy and local search for submodular maximization, while its first-order analogue is sufficient for projected gradient descent on convex minimization. Motivated by this notion, we formalize a trajectory-learning framework comprising trajectory construction, trajectory modeling, and candidate generation, and analyze existing trajectory-based methods under it. We further propose Uncertainty-aware Gradient-guided Trajectory Learning (UGTL), which constructs locally coherent improvement trajectories reflecting plausible search paths, models them with conditional diffusion, and selects a diverse candidate set. Our experiments show that UGTL achieves the best average rank, 3.1/25, among 25 methods on Design-Bench tasks, and confirm that our trajectory construction plays a significant role in the improvement. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.AI). Categorie arXiv: Machine Learning (cs.LG) ; Artificial Intelligence (cs.AI); Neural and Evolutionary Computing (cs.NE). Pagina del lavoro: https://arxiv.org/abs/2609.01493 — 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 2026-10-17T06:15:12.903Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).