Control-Variate Zeroth-Order Descent (CV-ZOD) is introduced, a new framework that refines the classical zeroth-order gradient estimator with a control variate that can be set based on the directional hints to leverage these hints adaptively while maintaining robustness to their quality.
Abstract
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.
It is proved that if $\mathcal G_N(\mathcal A)$ denotes the bound on the squared gradient norm after $N$ iterations for a method $\mathcal A, it is proved that $\limsup_{N\to\infty}N \mathcal G_N(\mathcal A) \ge 1/2$ for any method $\mathcal A$.
Zeroth-order optimization methods are essential for solving black-box problems where gradient information is unavailable or expensive to compute. This paper presents POEM-ES, a novel parameter-free stochastic zeroth-order algorithm that extends the recent POEM method by integrating subspace preconditioning with ellipso...
An alternative to the standard random gradient estimator is introduced, allowing for the projection step of spectral descent to be done at no extra cost and it is shown that by exploiting this low-rank property one obtains much faster convergence to good approximate solutions.
S. Allen, Cash Cherry, Aidan Eck et al.· 0 citations
We study nonconvex--strongly-convex bilevel optimization under a stochastic first-order oracle. We introduce MRT-FD, a single-loop first-order method that simultaneously tracks the upper-level variable, the lower-level solution, and the auxiliary response arising from implicit differentiation of the hyperobjective. MRT...
Powell asked whether the smoothness assumptions underlying classical superlinear convergence force a fixed power law between adjacent iterates of exact-line-search variable-metric methods. We answer this question negatively for BFGS: within the smooth strongly convex setting, the smallest possible adjacent-iterate Q-or...
This work proposes a novel single-loop algorithm based on a constrained reformulation in which lower-level stationarity is imposed as a constraint, and constructs a regularized Lagrangian by introducing a quadratic regularizer and restricting the dual variable to a bounded domain.
By studying the computational foundations of language learning, Associate Professor Jacob Andreas builds intelligent systems that can communicate effectively with humans.
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026