This study explores the performance of a random Gaussian smoothing zeroth-order (ZO) scheme for minimising quasar-convex (QC) and strongly quasar-convex (SQC) functions in both unconstrained and constrained settings. For the unconstrained problem, we establish the ZO algorithm's convergence to a global minimum along with its complexity when applied to both QC and SQC functions. For the constrained problem, we introduce the new notion of proximal-quasar-convexity and prove analogous results to the unconstrained case. Specifically, we show the complexity bounds and the convergence of the algorithm to a neighbourhood of a global minimum whose size can be controlled under a variance reduction scheme. Theoretical findings are illustrated through investigating the performance of the algorithm applied to a range of problems in machine learning and optimisation. Specifically, we observe scenarios where the ZO method outperforms gradient descent. We provide a possible explanation for this phenomenon.
View on arXiv@article{farzin2025_2505.02281,
title={ Minimisation of Quasar-Convex Functions Using Random Zeroth-Order Oracles },
author={ Amir Ali Farzin and Yuen-Man Pun and Iman Shames },
journal={arXiv preprint arXiv:2505.02281},
year={ 2025 }
}