# A Principle for Global Optimization with Gradients

arXiv: https://arxiv.org/abs/2308.09556 · HTML: https://mlsanity.com/paper/2308.09556/

## Key facts

- Cited by 1 papers 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 (most cited first, 6 of 6)

- [Evolution Strategies as a Scalable Alternative to Reinforcement Learning](https://mlsanity.com/paper/1703.03864/) (2017)
- [TREGO: a Trust-Region Framework for Efficient Global Optimization](https://mlsanity.com/paper/2101.06808/) (2021)
- [Derivative-Free Optimization of Noisy Functions via Quasi-Newton Methods](https://mlsanity.com/paper/1803.10173/) (2018)
- [Optimization and Learning With Nonlocal Calculus](https://mlsanity.com/paper/2012.07013/) (2020)
- [Linear interpolation gives better gradients than Gaussian smoothing in derivative-free optimization](https://mlsanity.com/paper/1905.13043/) (2019)
- [Non-local Optimization: Imposing Structure on Optimization Problems by Relaxation](https://mlsanity.com/paper/2011.06064/) (2020)

## Built on by (most cited first, 1 of 1)

- [Green-ELM: Efficient Analytic Learning via High-Dimensional Random Projections](https://mlsanity.com/paper/2604.15613/) (2026)

## 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.