A note on the complexity of random subspace model-based methods for derivative-free optimization
Coralia Cartis, Lindon Roberts
Abstract
We demonstrate that, with a suitable rescaling, using Johnson-Lindenstrauss transforms (JLTs) in the random subspace model-based derivative-free optimization (DFO) algorithm from [Cartis & Roberts, Math. Prog. 199 (2023)] achieves an improved worst-case evaluation complexity bound compared to 'unscaled' JLTs. This improved bound does not require any modification to the original algorithm or complexity analysis, and matches the best-known bound in terms of dimension dependence for model-based DFO (e.g. achieved by [Scheinberg & Chaudhry, ICM 2026] using Haar matrices in a similar framework).
Create a lesson
Related papers
Level-Set Geometry and the Theoretical Performance of PDHG for Conic Linear Optimization
Zikai Xiong, Robert M. Freund
Trajectory Manifolds for Nonlinear Data-Enabled Predictive Control
Arda Bayer
Optimizing Lyapunov Certificates via Stability-Preserving Quadratization for Polynomial Systems
Yubo Cai, Gioele Zardini
Regularity of a Multidimensional Principal-Agent Problem with Separable Effort Costs
Shuaijie Qian, Guan Qiao
Near-Optimal Exact-Value Zeroth-Order Complexity for Smooth Strongly Convex Optimization
Wendao Wu, Haihan Zhang, Chenheng Zhang et al.
A VU-calculus for composite functions and the U-Hessian of partly smooth functions
Shuai Liu