Metraipolis › archive › dc_7ef3fe8b0efb
Adaptively Incorporating Directional Hints into Zeroth-Order Optimization — arXiv:2609.08277
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08277
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:58:12.314Z
- SHA-256 of the archived text
7681b4705721f05c5acce3a2b8a1a346f69bdc5ab494a7e62eeb6d93ab0428a9- Stable URL of this page
https://metraipolis.com/documento/dc_7ef3fe8b0efb
How to cite
Adaptively Incorporating Directional Hints into Zeroth-Order Optimization — arXiv:2609.08277 — arXiv (en), https://arxiv.org/abs/2609.08277 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7ef3fe8b0efb (Metraipolis archive dc_7ef3fe8b0efb, sha256 7681b4705721f05c5acce3a2b8a1a346f69bdc5ab494a7e62eeb6d93ab0428a9)
BibTeX
@misc{dc7ef3fe8b0efb,
title = {Adaptively Incorporating Directional Hints into Zeroth-Order Optimization — arXiv:2609.08277},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08277},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7ef3fe8b0efb; sha256 7681b4705721f05c5acce3a2b8a1a346f69bdc5ab494a7e62eeb6d93ab0428a9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08277. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study zeroth-order optimization of non-convex functions with the aid of directional hints, which are cheap but potentially inaccurate approximations of the true gradient direction, given by linear subspaces at each iteration. To leverage these hints adaptively while maintaining robustness to their quality, we introduce Control-Variate Zeroth-Order Descent (CV-ZOD), a new framework that refines the classical zeroth-order gradient estimator with a control variate that can be set based on the directional hints. We first show that the oracle algorithm that optimally sets the reference vector and step size at each iteration achieves a convergence rate that interpolates between the first-order $O(1/T)$ rate and the zeroth-order $O(d/T)$ rate, depending on the quality of the hints along the trajectory. We then develop a practical variant of CV-ZOD that achieves the same oracle guarantee up to logarithmic factors, without any prior knowledge of the hint quality. We validate the method empirically on simulation-based scientific optimization tasks, demonstrating sustained progress on non-convex landscapes where zeroth-order descent is slower and existing guided methods stall as guidance deteriorates. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Optimization and Control (math.OC). Pagina del lavoro: https://arxiv.org/abs/2609.08277 — 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 2026-10-16T13:39:43.032Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).