Derivative-Free Global Optimization Algorithms: Population based Methods and Random Search Approaches
It provides an incremental overview of existing algorithms for researchers in machine learning, focusing on derivative-free methods to potentially enhance deep learning training.
This paper introduces derivative-free global optimization algorithms, such as population-based methods and random search approaches, to address the problem of gradient descent getting stuck in local optima when training deep learning models, aiming to improve training performance.
In this paper, we will provide an introduction to the derivative-free optimization algorithms which can be potentially applied to train deep learning models. Existing deep learning model training is mostly based on the back propagation algorithm, which updates the model variables layers by layers with the gradient descent algorithm or its variants. However, the objective functions of deep learning models to be optimized are usually non-convex and the gradient descent algorithms based on the first-order derivative can get stuck into the local optima very easily. To resolve such a problem, various local or global optimization algorithms have been proposed, which can help improve the training of deep learning models greatly. The representative examples include the Bayesian methods, Shubert-Piyavskii algorithm, Direct, LIPO, MCS, GA, SCE, DE, PSO, ES, CMA-ES, hill climbing and simulated annealing, etc. This is a follow-up paper of [18], and we will introduce the population based optimization algorithms, e.g., GA, SCE, DE, PSO, ES and CMA-ES, and random search algorithms, e.g., hill climbing and simulated annealing, in this paper. For the introduction to the other derivative-free optimization algorithms, please refer to [18] for more information.