A Principle for Global Optimization with Gradients
Not on the map. Why?
Abstract (arXiv)
This work demonstrates the utility of gradients for the global optimization of certain differentiable functions with many suboptimal local minima. To this end, a principle for generating search directions from non-local quadratic approximants based on gradients of the objective function is analyzed. Experiments measure the quality of non-local search directions as well as the performance of a proposed simplistic algorithm, of the covariance matrix adaptation evolution strategy (CMA-ES), and of a randomly reinitialized Broyden-Fletcher-Goldfarb-Shanno (BFGS) method.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 6 of its 48 references that are in the map. First posted on arXiv 18 Aug 2023.
Builds on
6 of 48 references.
References · 6
- 2017Evolution Strategies as a Scalable Alternative to Reinforcement Learningcited by 574
- 2021TREGO: a Trust-Region Framework for Efficient Global Optimizationcited by 29
- 2018Derivative-Free Optimization of Noisy Functions via Quasi-Newton Methodscited by 7
- 2020Optimization and Learning With Nonlocal Calculuscited by 5
- 2019Linear interpolation gives better gradients than Gaussian smoothing in derivative-free optimizationcited by 3
- 2020Non-local Optimization: Imposing Structure on Optimization Problems by Relaxationcited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.