SOURCE-LINKED INTELLIGENCE

Adaptively Incorporating Directional Hints into Zeroth-Order Optimization

arXiv · AI, language, vision and robotics · article · Sep 8, 2026 · UTC

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 an

Read original source ↗ Open in workspace

recordType

paper

region

Global