Curvature-Aware Derivative-Free Optimization
Kim, Bumsu, Cai, HanQin, McKenzie, Daniel, Yin, Wotao
–arXiv.org Artificial Intelligence
The paper discusses derivative-free optimization (DFO), which involves minimizing a function without access to gradients or directional derivatives, only function evaluations. Classical DFO methods, which mimic gradient-based methods, such as Nelder-Mead and direct search have limited scalability for high-dimensional problems. Zeroth-order methods have been gaining popularity due to the demands of large-scale machine learning applications, and the paper focuses on the selection of the step size $\alpha_k$ in these methods. The proposed approach, called Curvature-Aware Random Search (CARS), uses first- and second-order finite difference approximations to compute a candidate $\alpha_{+}$. We prove that for strongly convex objective functions, CARS converges linearly provided that the search direction is drawn from a distribution satisfying very mild conditions. We also present a Cubic Regularized variant of CARS, named CARS-CR, which converges in a rate of $\mathcal{O}(k^{-1})$ without the assumption of strong convexity. Numerical experiments show that CARS and CARS-CR match or exceed the state-of-the-arts on benchmark problem sets.
arXiv.org Artificial Intelligence
Apr-12-2023
- Country:
- Europe > Russia (0.04)
- Asia > Russia (0.04)
- North America > United States
- Florida > Orange County
- Orlando (0.04)
- Colorado > Jefferson County
- Golden (0.04)
- California > Los Angeles County
- Los Angeles (0.14)
- Florida > Orange County
- Africa > Senegal
- Kolda Region > Kolda (0.04)
- Genre:
- Research Report > New Finding (0.46)
- Technology: