A Survey of Optimization Methods From a Machine Learning Perspective

• Published in: IEEE transactions on cybernetics Vol. 50; no. 8; pp. 3668 - 3681
• Main Authors: Sun, Shiliang, Cao, Zehui, Zhu, Han, Zhao, Jing
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.08.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Approximate Bayesian inference; deep neural network (DNN); Linear programming; Machine learning; Machine learning algorithms; Optimization; optimization method; Optimization methods; reinforcement learning (RL); Stochastic processes; Task analysis
• ISSN: 2168-2267; 2168-2275; 2168-2275
• DOI: 10.1109/TCYB.2019.2950779

Machine learning develops rapidly, which has made many theoretical breakthroughs and is widely applied in various fields. Optimization, as an important part of machine learning, has attracted much attention of researchers. With the exponential growth of data amount and the increase of model complexity, optimization methods in machine learning face more and more challenges. A lot of work on solving optimization problems or improving optimization methods in machine learning has been proposed successively. The systematic retrospect and summary of the optimization methods from the perspective of machine learning are of great significance, which can offer guidance for both developments of optimization and machine learning research. In this article, we first describe the optimization problems in machine learning. Then, we introduce the principles and progresses of commonly used optimization methods. Finally, we explore and give some challenges and open problems for the optimization in machine learning.